{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/policy-gradient-methods","name":"Policy Gradient Methods","slug":"policy-gradient-methods","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":382,"papers_with_code":103,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/hanabi-learning-environment","name":"Hanabi Learning Environment","full_name":"","num_papers_in_archive":10},{"url":"/dataset/rllab-framework","name":"RLLab Framework","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":382,"of_with_code":103,"tagged_in_all":382,"counts":{"archive_papers_tagged":382,"with_a_code_link":103,"where_syntology_ran_a_sample":33,"not_listed_spam_title":0,"listed":382,"listed_where_code_ran":33,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":32,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":32,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/proximal-policy-optimization-algorithms","slug":"proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","arxiv_id":"1707.06347","repositories_listed":188,"syntology":{"n":176,"n_ran":99,"n_constructed":53,"n_ran_checked":71,"n_instrument":28,"n_unverified":77,"n_honours":7,"n_violates":2,"n_no_contract":62,"n_pointer_only":94,"phrase":"99 ran (of which 53 constructed an object rather than computing a result; 71 with no instrument failure: 7 honoured, 2 violated, 62 with no contract checked; 28 where Syntology's instrument failed) · 77 unverified","sample_list":"/paper/proximal-policy-optimization-algorithms#ran","syntology_url":"https://syntology.ai/paper/1707.06347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1707.06347"}},"official":null}},{"url":"/paper/self-critical-sequence-training-for-image","slug":"self-critical-sequence-training-for-image","title":"Self-critical Sequence Training for Image Captioning","date":"2016-12-02","arxiv_id":"1612.00563","repositories_listed":31,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":5,"n_instrument":7,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/self-critical-sequence-training-for-image#ran","syntology_url":"https://syntology.ai/paper/1612.00563","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.00563"}},"official":null}},{"url":"/paper/trust-region-policy-optimization","slug":"trust-region-policy-optimization","title":"Trust Region Policy Optimization","date":"2015-02-19","arxiv_id":"1502.05477","repositories_listed":24,"syntology":{"n":17,"n_ran":7,"n_constructed":2,"n_ran_checked":6,"n_instrument":1,"n_unverified":10,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/trust-region-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/1502.05477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.05477"}},"official":null}},{"url":"/paper/high-dimensional-continuous-control-using","slug":"high-dimensional-continuous-control-using","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","date":"2015-06-08","arxiv_id":"1506.02438","repositories_listed":17,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/high-dimensional-continuous-control-using#ran","syntology_url":"https://syntology.ai/paper/1506.02438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.02438"}},"official":null}},{"url":"/paper/deep-reinforcement-learning-for-dialogue","slug":"deep-reinforcement-learning-for-dialogue","title":"Deep Reinforcement Learning for Dialogue Generation","date":"2016-06-05","arxiv_id":"1606.01541","repositories_listed":8,"syntology":null},{"url":"/paper/competitive-policy-optimization","slug":"competitive-policy-optimization","title":"Competitive Policy Optimization","date":"2020-06-18","arxiv_id":"2006.10611","repositories_listed":4,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/competitive-policy-optimization#ran","syntology_url":"https://syntology.ai/paper/2006.10611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10611"}},"official":{"repos":["manish-pra/copg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/is-reinforcement-learning-not-for-natural","slug":"is-reinforcement-learning-not-for-natural","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","date":"2022-10-03","arxiv_id":"2210.01241","repositories_listed":3,"syntology":null},{"url":"/paper/distributional-policy-optimization-an","slug":"distributional-policy-optimization-an","title":"Distributional Policy Optimization: An Alternative Approach for Continuous Control","date":"2019-05-23","arxiv_id":"1905.09855","repositories_listed":3,"syntology":null},{"url":"/paper/rethinking-action-spaces-for-reinforcement","slug":"rethinking-action-spaces-for-reinforcement","title":"Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models","date":"2019-02-23","arxiv_id":"1902.08858","repositories_listed":3,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/rethinking-action-spaces-for-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1902.08858","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.08858"}},"official":{"repos":["snakeztc/NeuralDialog-LaRL"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reevaluating-policy-gradient-methods-for","slug":"reevaluating-policy-gradient-methods-for","title":"Reevaluating Policy Gradient Methods for Imperfect-Information Games","date":"2025-02-13","arxiv_id":"2502.08938","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reevaluating-policy-gradient-methods-for#ran","syntology_url":"https://syntology.ai/paper/2502.08938","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.08938"}},"official":{"repos":["gabrfarina/exp-a-spiel","nathanlct/iig-rl-benchmark"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/policy-gradient-methods-in-the-presence-of","slug":"policy-gradient-methods-in-the-presence-of","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","date":"2023-05-09","arxiv_id":"2305.05666","repositories_listed":2,"syntology":null},{"url":"/paper/experimental-design-for-mri-by-greedy-policy","slug":"experimental-design-for-mri-by-greedy-policy","title":"Experimental design for MRI by greedy policy search","date":"2020-10-30","arxiv_id":"2010.16262","repositories_listed":2,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":3,"n_no_contract":11,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 3 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/experimental-design-for-mri-by-greedy-policy#ran","syntology_url":"https://syntology.ai/paper/2010.16262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.16262"}},"official":{"repos":["Timsey/pg_mri"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lifelong-policy-gradient-learning-of-factored","slug":"lifelong-policy-gradient-learning-of-factored","title":"Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting","date":"2020-07-14","arxiv_id":"2007.07011","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/lifelong-policy-gradient-learning-of-factored#ran","syntology_url":"https://syntology.ai/paper/2007.07011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.07011"}},"official":{"repos":["GRASP-ML/LPG-FTW"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"url":"/paper/deep-reinforcement-learning-algorithm-for","slug":"deep-reinforcement-learning-algorithm-for","title":"Deep Reinforcement Learning Algorithm for Dynamic Pricing of Express Lanes with Multiple Access Locations","date":"2019-09-10","arxiv_id":"1909.04760","repositories_listed":2,"syntology":null},{"url":"/paper/rethink-global-reward-game-and-credit","slug":"rethink-global-reward-game-and-credit","title":"Shapley Q-value: A Local Reward Approach to Solve Global Reward Games","date":"2019-07-11","arxiv_id":"1907.05707","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/rethink-global-reward-game-and-credit#ran","syntology_url":"https://syntology.ai/paper/1907.05707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05707"}},"official":{"repos":["hsvgbkhgbv/SQDDPG"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/explainable-knowledge-graph-based","slug":"explainable-knowledge-graph-based","title":"Ekar: An Explainable Method for Knowledge Aware Recommendation","date":"2019-06-22","arxiv_id":"1906.09506","repositories_listed":2,"syntology":null},{"url":"/paper/trajectory-based-off-policy-deep","slug":"trajectory-based-off-policy-deep","title":"Trajectory-Based Off-Policy Deep Reinforcement Learning","date":"2019-05-14","arxiv_id":"1905.05710","repositories_listed":2,"syntology":null},{"url":"/paper/on-policy-trust-region-policy-optimisation","slug":"on-policy-trust-region-policy-optimisation","title":"On-Policy Trust Region Policy Optimisation with Replay Buffers","date":"2019-01-18","arxiv_id":"1901.06212","repositories_listed":2,"syntology":null},{"url":"/paper/remember-and-forget-for-experience-replay","slug":"remember-and-forget-for-experience-replay","title":"Remember and Forget for Experience Replay","date":"2018-07-16","arxiv_id":"1807.05827","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/remember-and-forget-for-experience-replay#ran","syntology_url":"https://syntology.ai/paper/1807.05827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.05827"}},"official":{"repos":["cselab/smarties"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-exploration-in-evolution-strategies","slug":"improving-exploration-in-evolution-strategies","title":"Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents","date":"2017-12-18","arxiv_id":"1712.06560","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-exploration-in-evolution-strategies#ran","syntology_url":"https://syntology.ai/paper/1712.06560","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.06560"}},"official":{"repos":["uber-research/deep-neuroevolution"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/action-depedent-control-variates-for-policy","slug":"action-depedent-control-variates-for-policy","title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity","date":"2017-10-30","arxiv_id":"1710.11198","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/action-depedent-control-variates-for-policy#ran","syntology_url":"https://syntology.ai/paper/1710.11198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11198"}},"official":null}},{"url":"/paper/q-prop-sample-efficient-policy-gradient-with","slug":"q-prop-sample-efficient-policy-gradient-with","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","date":"2016-11-07","arxiv_id":"1611.02247","repositories_listed":2,"syntology":null},{"url":"/paper/direct-retrieval-augmented-optimization","slug":"direct-retrieval-augmented-optimization","title":"Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models","date":"2025-05-05","arxiv_id":"2505.03075","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-policy-gradient-reinforcement","slug":"hierarchical-policy-gradient-reinforcement","title":"Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets","date":"2025-04-03","arxiv_id":"2504.02479","repositories_listed":1,"syntology":null},{"url":"/paper/convergence-guarantees-of-model-free-policy","slug":"convergence-guarantees-of-model-free-policy","title":"Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic Data","date":"2025-02-27","arxiv_id":"2502.19977","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-discrete-diffusion-models-with","slug":"fine-tuning-discrete-diffusion-models-with","title":"Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods","date":"2025-02-03","arxiv_id":"2502.01384","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":6,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fine-tuning-discrete-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2502.01384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01384"}},"official":{"repos":["ozekri/SEPO"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/divergence-augmented-policy-optimization-1","slug":"divergence-augmented-policy-optimization-1","title":"Divergence-Augmented Policy Optimization","date":"2025-01-25","arxiv_id":"2501.15034","repositories_listed":1,"syntology":null},{"url":"/paper/an-attentive-graph-agent-for-topology","slug":"an-attentive-graph-agent-for-topology","title":"An Attentive Graph Agent for Topology-Adaptive Cyber Defence","date":"2025-01-24","arxiv_id":"2501.14700","repositories_listed":1,"syntology":null},{"url":"/paper/multilinear-tensor-low-rank-approximation-for","slug":"multilinear-tensor-low-rank-approximation-for","title":"Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement Learning","date":"2025-01-08","arxiv_id":"2501.04879","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-an-overview","slug":"reinforcement-learning-an-overview","title":"Reinforcement Learning: An Overview","date":"2024-12-06","arxiv_id":"2412.05265","repositories_listed":1,"syntology":null},{"url":"/paper/deep-policy-gradient-methods-without-batch","slug":"deep-policy-gradient-methods-without-batch","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","date":"2024-11-22","arxiv_id":"2411.15370","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/deep-policy-gradient-methods-without-batch#ran","syntology_url":"https://syntology.ai/paper/2411.15370","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15370"}},"official":{"repos":["gauthamvasan/avg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-gradient-for-robust-markov-decision","slug":"policy-gradient-for-robust-markov-decision","title":"Policy Gradient for Robust Markov Decision Processes","date":"2024-10-29","arxiv_id":"2410.22114","repositories_listed":1,"syntology":null},{"url":"/paper/steptool-a-step-grained-reinforcement","slug":"steptool-a-step-grained-reinforcement","title":"StepTool: A Step-grained Reinforcement Learning Framework for Tool Learning in LLMs","date":"2024-10-10","arxiv_id":"2410.07745","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/steptool-a-step-grained-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2410.07745","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07745"}},"official":{"repos":["yuyq18/steptool"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/near-optimal-policy-identification-in-robust","slug":"near-optimal-policy-identification-in-robust","title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","date":"2024-08-29","arxiv_id":"2408.16286","repositories_listed":1,"syntology":null},{"url":"/paper/matrix-low-rank-approximation-for-policy","slug":"matrix-low-rank-approximation-for-policy","title":"Matrix Low-Rank Approximation For Policy Gradient Methods","date":"2024-05-27","arxiv_id":"2405.17626","repositories_listed":1,"syntology":null},{"url":"/paper/self-improvement-for-neural-combinatorial","slug":"self-improvement-for-neural-combinatorial","title":"Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement","date":"2024-03-22","arxiv_id":"2403.15180","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 2 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/self-improvement-for-neural-combinatorial#ran","syntology_url":"https://syntology.ai/paper/2403.15180","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15180"}},"official":{"repos":["grimmlab/gumbeldore"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/predictable-reinforcement-learning-dynamics","slug":"predictable-reinforcement-learning-dynamics","title":"Predictable Reinforcement Learning Dynamics through Entropy Rate Minimization","date":"2023-11-30","arxiv_id":"2311.18703","repositories_listed":1,"syntology":null},{"url":"/paper/clipped-objective-policy-gradients-for","slug":"clipped-objective-policy-gradients-for","title":"Clipped-Objective Policy Gradients for Pessimistic Policy Optimization","date":"2023-11-10","arxiv_id":"2311.05846","repositories_listed":1,"syntology":null},{"url":"/paper/accelerated-policy-gradient-on-the-nesterov","slug":"accelerated-policy-gradient-on-the-nesterov","title":"Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning","date":"2023-10-18","arxiv_id":"2310.11897","repositories_listed":1,"syntology":null},{"url":"/paper/oracle-complexity-reduction-for-model-free","slug":"oracle-complexity-reduction-for-model-free","title":"Oracle Complexity Reduction for Model-free LQR: A Stochastic Variance-Reduced Policy Gradient Approach","date":"2023-09-19","arxiv_id":"2309.10679","repositories_listed":1,"syntology":null},{"url":"/paper/learning-zero-sum-linear-quadratic-games-with","slug":"learning-zero-sum-linear-quadratic-games-with","title":"Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence","date":"2023-09-08","arxiv_id":"2309.04272","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-dice-stable-credit-assignment-for","slug":"hindsight-dice-stable-credit-assignment-for","title":"Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning","date":"2023-07-21","arxiv_id":"2307.11897","repositories_listed":1,"syntology":null},{"url":"/paper/feedback-is-all-you-need-real-world","slug":"feedback-is-all-you-need-real-world","title":"Enabling Efficient, Reliable Real-World Reinforcement Learning with Approximate Physics-Based Models","date":"2023-07-16","arxiv_id":"2307.08168","repositories_listed":1,"syntology":null},{"url":"/paper/neural-inventory-control-in-networks-via","slug":"neural-inventory-control-in-networks-via","title":"Neural Inventory Control in Networks via Hindsight Differentiable Policy Optimization","date":"2023-06-20","arxiv_id":"2306.11246","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-diffusion-policies-for-offline-1","slug":"efficient-diffusion-policies-for-offline-1","title":"Efficient Diffusion Policies for Offline Reinforcement Learning","date":"2023-05-31","arxiv_id":"2305.20081","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/efficient-diffusion-policies-for-offline-1#ran","syntology_url":"https://syntology.ai/paper/2305.20081","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20081"}},"official":{"repos":["sail-sg/edp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/client-selection-for-federated-policy","slug":"client-selection-for-federated-policy","title":"Client Selection for Federated Policy Optimization with Environment Heterogeneity","date":"2023-05-18","arxiv_id":"2305.10978","repositories_listed":1,"syntology":null},{"url":"/paper/online-portfolio-management-via-deep","slug":"online-portfolio-management-via-deep","title":"Online Portfolio Management via Deep Reinforcement Learning with High-Frequency Data","date":"2023-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/distributional-constrained-reinforcement","slug":"distributional-constrained-reinforcement","title":"Distributional constrained reinforcement learning for supply chain optimization","date":"2023-02-03","arxiv_id":"2302.01727","repositories_listed":1,"syntology":null},{"url":"/paper/partial-advantage-estimator-for-proximal","slug":"partial-advantage-estimator-for-proximal","title":"Partial advantage estimator for proximal policy optimization","date":"2023-01-26","arxiv_id":"2301.10920","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-convergence-of-policy-gradient-in","slug":"on-the-convergence-of-policy-gradient-in","title":"Policy Gradient in Robust MDPs with Global Convergence Guarantee","date":"2022-12-20","arxiv_id":"2212.10439","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-mdp-homomorphisms-and-homomorphic","slug":"continuous-mdp-homomorphisms-and-homomorphic","title":"Continuous MDP Homomorphisms and Homomorphic Policy Gradient","date":"2022-09-15","arxiv_id":"2209.07364","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/continuous-mdp-homomorphisms-and-homomorphic#ran","syntology_url":"https://syntology.ai/paper/2209.07364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.07364"}},"official":{"repos":["sahandrez/homomorphic_policy_gradient"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/the-performance-impact-of-combining-agent","slug":"the-performance-impact-of-combining-agent","title":"The Performance Impact of Combining Agent Factorization with Different Learning Algorithms for Multiagent Coordination","date":"2022-09-09","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/reactive-exploration-to-cope-with-non","slug":"reactive-exploration-to-cope-with-non","title":"Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning","date":"2022-07-12","arxiv_id":"2207.05742","repositories_listed":1,"syntology":null},{"url":"/paper/sigmoidally-preconditioned-off-policy","slug":"sigmoidally-preconditioned-off-policy","title":"The Sufficiency of Off-Policyness and Soft Clipping: PPO is still Insufficient according to an Off-Policy Measure","date":"2022-05-20","arxiv_id":"2205.10047","repositories_listed":1,"syntology":null},{"url":"/paper/synthesis-of-stabilizing-recurrent","slug":"synthesis-of-stabilizing-recurrent","title":"Synthesis of Stabilizing Recurrent Equilibrium Network Controllers","date":"2022-03-31","arxiv_id":"2204.00122","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-class-abstraction-for-commonsense","slug":"leveraging-class-abstraction-for-commonsense","title":"Leveraging class abstraction for commonsense reinforcement learning via residual policy gradient methods","date":"2022-01-28","arxiv_id":"2201.12126","repositories_listed":1,"syntology":null},{"url":"/paper/bag-of-tricks-for-natural-policy-gradient","slug":"bag-of-tricks-for-natural-policy-gradient","title":"Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning","date":"2022-01-22","arxiv_id":"2201.09104","repositories_listed":1,"syntology":null},{"url":"/paper/mdpgt-momentum-based-decentralized-policy","slug":"mdpgt-momentum-based-decentralized-policy","title":"MDPGT: Momentum-based Decentralized Policy Gradient Tracking","date":"2021-12-06","arxiv_id":"2112.02813","repositories_listed":1,"syntology":null},{"url":"/paper/episodic-policy-gradient-training","slug":"episodic-policy-gradient-training","title":"Episodic Policy Gradient Training","date":"2021-12-03","arxiv_id":"2112.01853","repositories_listed":1,"syntology":null},{"url":"/paper/time-discretization-invariant-safe-action","slug":"time-discretization-invariant-safe-action","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","date":"2021-11-06","arxiv_id":"2111.03941","repositories_listed":1,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/time-discretization-invariant-safe-action#ran","syntology_url":"https://syntology.ai/paper/2111.03941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.03941"}},"official":{"repos":["artberryx/SAR"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/global-optimality-and-finite-sample-analysis","slug":"global-optimality-and-finite-sample-analysis","title":"Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch","date":"2021-11-04","arxiv_id":"2111.02997","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/global-optimality-and-finite-sample-analysis#ran","syntology_url":"https://syntology.ai/paper/2111.02997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.02997"}},"official":{"repos":["ShangtongZhang/DeepRL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transform2act-learning-a-transform-and","slug":"transform2act-learning-a-transform-and","title":"Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design","date":"2021-10-07","arxiv_id":"2110.03659","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transform2act-learning-a-transform-and#ran","syntology_url":"https://syntology.ai/paper/2110.03659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03659"}},"official":{"repos":["Khrylx/Transform2Act"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-opinion-summarizers-by-selecting","slug":"learning-opinion-summarizers-by-selecting","title":"Learning Opinion Summarizers by Selecting Informative Reviews","date":"2021-09-09","arxiv_id":"2109.04325","repositories_listed":1,"syntology":null},{"url":"/paper/a-functional-mirror-ascent-view-of-policy","slug":"a-functional-mirror-ascent-view-of-policy","title":"A general class of surrogate functions for stable and efficient reinforcement learning","date":"2021-08-12","arxiv_id":"2108.05828","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-value-function-for-variance","slug":"hindsight-value-function-for-variance","title":"Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment","date":"2021-07-26","arxiv_id":"2107.12216","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/hindsight-value-function-for-variance#ran","syntology_url":"https://syntology.ai/paper/2107.12216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.12216"}},"official":null}},{"url":"/paper/model-free-policy-learning-with-reward","slug":"model-free-policy-learning-with-reward","title":"Model-free Policy Learning with Reward Gradients","date":"2021-03-09","arxiv_id":"2103.05147","repositories_listed":1,"syntology":null},{"url":"/paper/model-free-and-bayesian-ensembling-model","slug":"model-free-and-bayesian-ensembling-model","title":"Model-free and Bayesian Ensembling Model-based Deep Reinforcement Learning for Particle Accelerator Control Demonstrated on the FERMI FEL","date":"2020-12-17","arxiv_id":"2012.09737","repositories_listed":1,"syntology":null},{"url":"/paper/an-efficient-asynchronous-method-for-1","slug":"an-efficient-asynchronous-method-for-1","title":"An Efficient Asynchronous Method for Integrating Evolutionary and Gradient-based Policy Search","date":"2020-12-10","arxiv_id":"2012.05417","repositories_listed":1,"syntology":null},{"url":"/paper/learning-multi-agent-communication-through","slug":"learning-multi-agent-communication-through","title":"Learning Multi-Agent Communication through Structured Attentive Reasoning","date":"2020-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/efficient-wasserstein-natural-gradients-for-1","slug":"efficient-wasserstein-natural-gradients-for-1","title":"Efficient Wasserstein Natural Gradients for Reinforcement Learning","date":"2020-10-12","arxiv_id":"2010.05380","repositories_listed":1,"syntology":null},{"url":"/paper/pc-pg-policy-cover-directed-exploration-for","slug":"pc-pg-policy-cover-directed-exploration-for","title":"PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning","date":"2020-07-16","arxiv_id":"2007.08459","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pc-pg-policy-cover-directed-exploration-for#ran","syntology_url":"https://syntology.ai/paper/2007.08459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.08459"}},"official":null}},{"url":"/paper/momentum-based-policy-gradient-methods","slug":"momentum-based-policy-gradient-methods","title":"Momentum-Based Policy Gradient Methods","date":"2020-07-13","arxiv_id":"2007.06680","repositories_listed":1,"syntology":null},{"url":"/paper/deep-bayesian-quadrature-policy-optimization","slug":"deep-bayesian-quadrature-policy-optimization","title":"Deep Bayesian Quadrature Policy Optimization","date":"2020-06-28","arxiv_id":"2006.15637","repositories_listed":1,"syntology":null},{"url":"/paper/learning-optimal-environments-using-projected","slug":"learning-optimal-environments-using-projected","title":"Jointly Learning Environments and Control Policies with Projected Stochastic Gradient Ascent","date":"2020-06-02","arxiv_id":"2006.01738","repositories_listed":1,"syntology":null},{"url":"/paper/invariant-policy-optimization-towards","slug":"invariant-policy-optimization-towards","title":"Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning","date":"2020-06-01","arxiv_id":"2006.01096","repositories_listed":1,"syntology":null},{"url":"/paper/policy-aware-model-learning-for-policy","slug":"policy-aware-model-learning-for-policy","title":"Policy-Aware Model Learning for Policy Gradient Methods","date":"2020-02-28","arxiv_id":"2003.00030","repositories_listed":1,"syntology":null},{"url":"/paper/provably-convergent-policy-gradient-methods","slug":"provably-convergent-policy-gradient-methods","title":"On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning","date":"2020-02-12","arxiv_id":"2002.05135","repositories_listed":1,"syntology":null},{"url":"/paper/a-nonparametric-offpolicy-policy-gradient","slug":"a-nonparametric-offpolicy-policy-gradient","title":"A Nonparametric Off-Policy Policy Gradient","date":"2020-01-08","arxiv_id":"2001.02435","repositories_listed":1,"syntology":null},{"url":"/paper/fast-efficient-hyperparameter-tuning-for-1","slug":"fast-efficient-hyperparameter-tuning-for-1","title":"Fast Efficient Hyperparameter Tuning for Policy Gradient Methods","date":"2019-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/v-mpo-on-policy-maximum-a-posteriori-policy","slug":"v-mpo-on-policy-maximum-a-posteriori-policy","title":"V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control","date":"2019-09-26","arxiv_id":"1909.12238","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/v-mpo-on-policy-maximum-a-posteriori-policy#ran","syntology_url":"https://syntology.ai/paper/1909.12238","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.12238"}},"official":null}},{"url":"/paper/sample-efficient-policy-gradient-methods-with","slug":"sample-efficient-policy-gradient-methods-with","title":"Sample Efficient Policy Gradient Methods with Recursive Variance Reduction","date":"2019-09-18","arxiv_id":"1909.08610","repositories_listed":1,"syntology":null},{"url":"/paper/health-informed-policy-gradients-for-multi","slug":"health-informed-policy-gradients-for-multi","title":"Health-Informed Policy Gradients for Multi-Agent Reinforcement Learning","date":"2019-08-02","arxiv_id":"1908.01022","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-trust-region-policy-optimization","slug":"hindsight-trust-region-policy-optimization","title":"Hindsight Trust Region Policy Optimization","date":"2019-07-29","arxiv_id":"1907.12439","repositories_listed":1,"syntology":null},{"url":"/paper/ranking-policy-gradient","slug":"ranking-policy-gradient","title":"Ranking Policy Gradient","date":"2019-06-24","arxiv_id":"1906.09674","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ranking-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/1906.09674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.09674"}},"official":{"repos":["illidanlab/rpg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/190600190","slug":"190600190","title":"Neural Replicator Dynamics","date":"2019-06-01","arxiv_id":"1906.00190","repositories_listed":1,"syntology":null},{"url":"/paper/neural-logic-reinforcement-learning","slug":"neural-logic-reinforcement-learning","title":"Neural Logic Reinforcement Learning","date":"2019-04-24","arxiv_id":"1904.10729","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/neural-logic-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/1904.10729","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10729"}},"official":{"repos":["ZhengyaoJiang/NLRL"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-rewards-for-question-generation","slug":"evaluating-rewards-for-question-generation","title":"Evaluating Rewards for Question Generation Models","date":"2019-02-28","arxiv_id":"1902.11049","repositories_listed":1,"syntology":null},{"url":"/paper/fast-efficient-hyperparameter-tuning-for","slug":"fast-efficient-hyperparameter-tuning-for","title":"Fast Efficient Hyperparameter Tuning for Policy Gradients","date":"2019-02-18","arxiv_id":"1902.06583","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/fast-efficient-hyperparameter-tuning-for#ran","syntology_url":"https://syntology.ai/paper/1902.06583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.06583"}},"official":null}},{"url":"/paper/bayesian-action-decoder-for-deep-multi-agent","slug":"bayesian-action-decoder-for-deep-multi-agent","title":"Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning","date":"2018-11-04","arxiv_id":"1811.01458","repositories_listed":1,"syntology":null},{"url":"/paper/actor-expert-a-framework-for-using-action","slug":"actor-expert-a-framework-for-using-action","title":"Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement","date":"2018-10-22","arxiv_id":"1810.09103","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/actor-expert-a-framework-for-using-action#ran","syntology_url":"https://syntology.ai/paper/1810.09103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.09103"}},"official":{"repos":["samuelfneumann/greedyac"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/where-did-my-optimum-go-an-empirical-analysis","slug":"where-did-my-optimum-go-an-empirical-analysis","title":"Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods","date":"2018-10-05","arxiv_id":"1810.02525","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/where-did-my-optimum-go-an-empirical-analysis#ran","syntology_url":"https://syntology.ai/paper/1810.02525","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.02525"}},"official":{"repos":["facebookresearch/WhereDidMyOptimumGo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/training-for-diversity-in-image-paragraph","slug":"training-for-diversity-in-image-paragraph","title":"Training for Diversity in Image Paragraph Captioning","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-goal-oriented-visual-dialog-via","slug":"learning-goal-oriented-visual-dialog-via","title":"Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient","date":"2018-07-02","arxiv_id":"1807.00737","repositories_listed":1,"syntology":null},{"url":"/paper/on-learning-intrinsic-rewards-for-policy","slug":"on-learning-intrinsic-rewards-for-policy","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","date":"2018-04-17","arxiv_id":"1804.06459","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":10,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/on-learning-intrinsic-rewards-for-policy#ran","syntology_url":"https://syntology.ai/paper/1804.06459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.06459"}},"official":{"repos":["Hwhitetooth/lirpg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/the-mirage-of-action-dependent-baselines-in","slug":"the-mirage-of-action-dependent-baselines-in","title":"The Mirage of Action-Dependent Baselines in Reinforcement Learning","date":"2018-02-27","arxiv_id":"1802.10031","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-mirage-of-action-dependent-baselines-in#ran","syntology_url":"https://syntology.ai/paper/1802.10031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.10031"}},"official":null}},{"url":"/paper/clipped-action-policy-gradient","slug":"clipped-action-policy-gradient","title":"Clipped Action Policy Gradient","date":"2018-02-21","arxiv_id":"1802.07564","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/clipped-action-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/1802.07564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07564"}},"official":{"repos":["pfnet-research/capg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bayesian-policy-gradients-via-alpha","slug":"bayesian-policy-gradients-via-alpha","title":"Bayesian Policy Gradients via Alpha Divergence Dropout Inference","date":"2017-12-06","arxiv_id":"1712.02037","repositories_listed":1,"syntology":null},{"url":"/paper/divide-and-conquer-reinforcement-learning","slug":"divide-and-conquer-reinforcement-learning","title":"Divide-and-Conquer Reinforcement Learning","date":"2017-11-27","arxiv_id":"1711.09874","repositories_listed":1,"syntology":null},{"url":"/paper/run-skeleton-run-skeletal-model-in-a-physics","slug":"run-skeleton-run-skeletal-model-in-a-physics","title":"Run, skeleton, run: skeletal model in a physics-based simulation","date":"2017-11-18","arxiv_id":"1711.06922","repositories_listed":1,"syntology":null},{"url":"/paper/hindsight-policy-gradients","slug":"hindsight-policy-gradients","title":"Hindsight policy gradients","date":"2017-11-16","arxiv_id":"1711.06006","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hindsight-policy-gradients#ran","syntology_url":"https://syntology.ai/paper/1711.06006","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.06006"}},"official":null}}],"syntology_records":34,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":33,"papers_where_code_ran_first_page":"/task/policy-gradient-methods/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/policy-gradient-methods/papers/2","json":"/task/policy-gradient-methods/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/policy-gradient-methods/papers/3","json":"/task/policy-gradient-methods/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/policy-gradient-methods/papers/4","json":"/task/policy-gradient-methods/papers/4.json","rows":82},{"order":"ran","page":1,"of":1,"url":"/task/policy-gradient-methods/papers/ran/1","json":"/task/policy-gradient-methods/papers/ran/1.json","rows":33}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"f160490d35ec0bc5cd03080145b2fe2391f1d7412e650a2186aa91fe22a8c150","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}