{"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/sequential-decision-making","name":"Sequential Decision Making","slug":"sequential-decision-making","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":1210,"papers_with_code":351,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/benyfits","name":"BeNYfits","full_name":"New York City Public Benefits Eligibility Dialog Agent Benchmark","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":13,"rows_per_page":100,"shown":100,"of":1210,"of_with_code":351,"tagged_in_all":1210,"counts":{"archive_papers_tagged":1210,"with_a_code_link":351,"where_syntology_ran_a_sample":107,"not_listed_spam_title":0,"listed":1210,"listed_where_code_ran":107,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":87,"every_run_a_failure_of_syntologys_instrument":20,"listed_with_a_run_with_no_instrument_failure":87,"listed_every_run_a_failure_of_syntologys_instrument":20,"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/deep-reinforcement-learning-for-unsupervised","slug":"deep-reinforcement-learning-for-unsupervised","title":"Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward","date":"2017-12-29","arxiv_id":"1801.00054","repositories_listed":6,"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-reinforcement-learning-for-unsupervised#ran","syntology_url":"https://syntology.ai/paper/1801.00054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.00054"}},"official":{"repos":["KaiyangZhou/vsumm-reinforce"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/reflexion-language-agents-with-verbal","slug":"reflexion-language-agents-with-verbal","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","date":"2023-03-20","arxiv_id":"2303.11366","repositories_listed":5,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":1,"phrase":"8 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/reflexion-language-agents-with-verbal#ran","syntology_url":"https://syntology.ai/paper/2303.11366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.11366"}},"official":{"repos":["noahshinn024/reflexion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/iq-learn-inverse-soft-q-learning-for","slug":"iq-learn-inverse-soft-q-learning-for","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","date":"2021-06-23","arxiv_id":"2106.12142","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/iq-learn-inverse-soft-q-learning-for#ran","syntology_url":"https://syntology.ai/paper/2106.12142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12142"}},"official":{"repos":["Div99/IQ-Learn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/deep-reinforcement-learning-based","slug":"deep-reinforcement-learning-based","title":"Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling","date":"2018-10-29","arxiv_id":"1810.12027","repositories_listed":5,"syntology":null},{"url":"/paper/deep-bayesian-bandits-showdown-an-empirical","slug":"deep-bayesian-bandits-showdown-an-empirical","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","date":"2018-02-26","arxiv_id":"1802.09127","repositories_listed":4,"syntology":null},{"url":"/paper/learning-multi-level-hierarchies-with","slug":"learning-multi-level-hierarchies-with","title":"Learning Multi-Level Hierarchies with Hindsight","date":"2017-12-04","arxiv_id":"1712.00948","repositories_listed":4,"syntology":null},{"url":"/paper/thinking-fast-and-slow-with-deep-learning-and","slug":"thinking-fast-and-slow-with-deep-learning-and","title":"Thinking Fast and Slow with Deep Learning and Tree Search","date":"2017-05-23","arxiv_id":"1705.08439","repositories_listed":4,"syntology":null},{"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/deep-reinforcement-learning-for-imbalanced","slug":"deep-reinforcement-learning-for-imbalanced","title":"Deep Reinforcement Learning for Imbalanced Classification","date":"2019-01-05","arxiv_id":"1901.01379","repositories_listed":3,"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/deep-reinforcement-learning-for-imbalanced#ran","syntology_url":"https://syntology.ai/paper/1901.01379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01379"}},"official":{"repos":["linenus/DRL-For-imbalanced-Classification"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a2-rl-aesthetics-aware-reinforcement-learning","slug":"a2-rl-aesthetics-aware-reinforcement-learning","title":"A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping","date":"2017-09-14","arxiv_id":"1709.04595","repositories_listed":3,"syntology":null},{"url":"/paper/an-alternative-softmax-operator-for","slug":"an-alternative-softmax-operator-for","title":"An Alternative Softmax Operator for Reinforcement Learning","date":"2016-12-16","arxiv_id":"1612.05628","repositories_listed":3,"syntology":null},{"url":"/paper/model-free-episodic-control","slug":"model-free-episodic-control","title":"Model-Free Episodic Control","date":"2016-06-14","arxiv_id":"1606.04460","repositories_listed":3,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/model-free-episodic-control#ran","syntology_url":"https://syntology.ai/paper/1606.04460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.04460"}},"official":null}},{"url":"/paper/multi-agent-reinforcement-learning-for-22","slug":"multi-agent-reinforcement-learning-for-22","title":"Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey","date":"2024-08-19","arxiv_id":"2408.09675","repositories_listed":2,"syntology":null},{"url":"/paper/adaptive-foundation-models-for-online","slug":"adaptive-foundation-models-for-online","title":"Scalable Exploration via Ensemble++","date":"2024-07-18","arxiv_id":"2407.13195","repositories_listed":2,"syntology":{"n":8,"n_ran":5,"n_constructed":1,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/adaptive-foundation-models-for-online#ran","syntology_url":"https://syntology.ai/paper/2407.13195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.13195"}},"official":{"repos":["szrlee/GPT-HyperAgent","szrlee/ensemble_plus_plus"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/sym-q-adaptive-symbolic-regression-via","slug":"sym-q-adaptive-symbolic-regression-via","title":"Sym-Q: Adaptive Symbolic Regression via Sequential Decision-Making","date":"2024-02-07","arxiv_id":"2402.05306","repositories_listed":2,"syntology":null},{"url":"/paper/zero-shot-reinforcement-learning-via-function","slug":"zero-shot-reinforcement-learning-via-function","title":"Zero-Shot Reinforcement Learning via Function Encoders","date":"2024-01-30","arxiv_id":"2401.17173","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-reinforcement-learning-via-function#ran","syntology_url":"https://syntology.ai/paper/2401.17173","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.17173"}},"official":{"repos":["anonymousresearcher5642/functionencoderrl","tyler-ingebrand/functionencoderrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/equal-long-term-benefit-rate-adapting-static","slug":"equal-long-term-benefit-rate-adapting-static","title":"Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate","date":"2023-09-07","arxiv_id":"2309.03426","repositories_listed":2,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/equal-long-term-benefit-rate-adapting-static#ran","syntology_url":"https://syntology.ai/paper/2309.03426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03426"}},"official":{"repos":["umd-huang-lab/elbert","yuancheng-xu/elbert"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/learning-embeddings-for-sequential-tasks","slug":"learning-embeddings-for-sequential-tasks","title":"Learning Embeddings for Sequential Tasks Using Population of Agents","date":"2023-06-05","arxiv_id":"2306.03311","repositories_listed":2,"syntology":null},{"url":"/paper/trieste-efficiently-exploring-the-depths-of","slug":"trieste-efficiently-exploring-the-depths-of","title":"Trieste: Efficiently Exploring The Depths of Black-box Functions with TensorFlow","date":"2023-02-16","arxiv_id":"2302.08436","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trieste-efficiently-exploring-the-depths-of#ran","syntology_url":"https://syntology.ai/paper/2302.08436","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.08436"}},"official":{"repos":["secondmind-labs/trieste"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/temporal-latent-bottleneck-synthesis-of-fast","slug":"temporal-latent-bottleneck-synthesis-of-fast","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","date":"2022-05-30","arxiv_id":"2205.14794","repositories_listed":2,"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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/temporal-latent-bottleneck-synthesis-of-fast#ran","syntology_url":"https://syntology.ai/paper/2205.14794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14794"}},"official":null}},{"url":"/paper/efficient-symptom-inquiring-and-diagnosis-via","slug":"efficient-symptom-inquiring-and-diagnosis-via","title":"Efficient Symptom Inquiring and Diagnosis via Adaptive Alignment of Reinforcement Learning and Classification","date":"2021-12-01","arxiv_id":"2112.00733","repositories_listed":2,"syntology":null},{"url":"/paper/mixed-policy-gradient","slug":"mixed-policy-gradient","title":"Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model","date":"2021-02-23","arxiv_id":"2102.11513","repositories_listed":2,"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":1,"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/mixed-policy-gradient#ran","syntology_url":"https://syntology.ai/paper/2102.11513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.11513"}},"official":null}},{"url":"/paper/text-based-rl-agents-with-commonsense","slug":"text-based-rl-agents-with-commonsense","title":"Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines","date":"2020-10-08","arxiv_id":"2010.03790","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/text-based-rl-agents-with-commonsense#ran","syntology_url":"https://syntology.ai/paper/2010.03790","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.03790"}},"official":{"repos":["IBM/commonsense-rl"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pddlgym-gym-environments-from-pddl-problems","slug":"pddlgym-gym-environments-from-pddl-problems","title":"PDDLGym: Gym Environments from PDDL Problems","date":"2020-02-15","arxiv_id":"2002.06432","repositories_listed":2,"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/pddlgym-gym-environments-from-pddl-problems#ran","syntology_url":"https://syntology.ai/paper/2002.06432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.06432"}},"official":{"repos":["tomsilver/pddlgym"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-learning-for-malaria-control","slug":"policy-learning-for-malaria-control","title":"Policy Learning for Malaria Control","date":"2019-10-20","arxiv_id":"1910.08926","repositories_listed":2,"syntology":null},{"url":"/paper/classification-with-costly-features-as-a","slug":"classification-with-costly-features-as-a","title":"Classification with Costly Features as a Sequential Decision-Making Problem","date":"2019-09-05","arxiv_id":"1909.02564","repositories_listed":2,"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/classification-with-costly-features-as-a#ran","syntology_url":"https://syntology.ai/paper/1909.02564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.02564"}},"official":{"repos":["jaromiru/cwcf"],"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/skipnet-learning-dynamic-routing-in","slug":"skipnet-learning-dynamic-routing-in","title":"SkipNet: Learning Dynamic Routing in Convolutional Networks","date":"2017-11-26","arxiv_id":"1711.09485","repositories_listed":2,"syntology":null},{"url":"/paper/detecting-adversarial-attacks-on-neural","slug":"detecting-adversarial-attacks-on-neural","title":"Detecting Adversarial Attacks on Neural Network Policies with Visual Foresight","date":"2017-10-02","arxiv_id":"1710.00814","repositories_listed":2,"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":10,"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/detecting-adversarial-attacks-on-neural#ran","syntology_url":"https://syntology.ai/paper/1710.00814","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.00814"}},"official":{"repos":["yenchenlin/rl-attack-detection"],"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/learning-model-based-planning-from-scratch","slug":"learning-model-based-planning-from-scratch","title":"Learning model-based planning from scratch","date":"2017-07-19","arxiv_id":"1707.06170","repositories_listed":2,"syntology":null},{"url":"/paper/doubly-robust-off-policy-value-evaluation-for","slug":"doubly-robust-off-policy-value-evaluation-for","title":"Doubly Robust Off-policy Value Evaluation for Reinforcement Learning","date":"2015-11-11","arxiv_id":"1511.03722","repositories_listed":2,"syntology":null},{"url":"/paper/uprop-investigating-the-uncertainty","slug":"uprop-investigating-the-uncertainty","title":"UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making","date":"2025-06-20","arxiv_id":"2506.17419","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-action-duration-with-contextual","slug":"adaptive-action-duration-with-contextual","title":"Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments","date":"2025-06-17","arxiv_id":"2507.00030","repositories_listed":1,"syntology":null},{"url":"/paper/common-benchmarks-undervalue-the","slug":"common-benchmarks-undervalue-the","title":"Common Benchmarks Undervalue the Generalization Power of Programmatic Policies","date":"2025-06-17","arxiv_id":"2506.14162","repositories_listed":1,"syntology":null},{"url":"/paper/textatari-100k-frames-game-playing-with","slug":"textatari-100k-frames-game-playing-with","title":"TextAtari: 100K Frames Game Playing with Language Agents","date":"2025-06-04","arxiv_id":"2506.04098","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/textatari-100k-frames-game-playing-with#ran","syntology_url":"https://syntology.ai/paper/2506.04098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.04098"}},"official":{"repos":["Lww007/Text-Atari-Agents"],"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/large-language-models-for-planning-a","slug":"large-language-models-for-planning-a","title":"Large Language Models for Planning: A Comprehensive and Systematic Survey","date":"2025-05-26","arxiv_id":"2505.19683","repositories_listed":1,"syntology":null},{"url":"/paper/web-shepherd-advancing-prms-for-reinforcing","slug":"web-shepherd-advancing-prms-for-reinforcing","title":"Web-Shepherd: Advancing PRMs for Reinforcing Web Agents","date":"2025-05-21","arxiv_id":"2505.15277","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":1,"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/web-shepherd-advancing-prms-for-reinforcing#ran","syntology_url":"https://syntology.ai/paper/2505.15277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15277"}},"official":{"repos":["kyle8581/Web-Shepherd"],"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/sample-and-computationally-efficient-1","slug":"sample-and-computationally-efficient-1","title":"Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation","date":"2025-05-20","arxiv_id":"2505.14821","repositories_listed":1,"syntology":null},{"url":"/paper/texttt-llinbo-trustworthy-llm-in-the-loop","slug":"texttt-llinbo-trustworthy-llm-in-the-loop","title":"$\\texttt{LLINBO}$: Trustworthy LLM-in-the-Loop Bayesian Optimization","date":"2025-05-20","arxiv_id":"2505.14756","repositories_listed":1,"syntology":null},{"url":"/paper/comparing-exploration-exploitation-strategies","slug":"comparing-exploration-exploitation-strategies","title":"Comparing Exploration-Exploitation Strategies of LLMs and Humans: Insights from Standard Multi-armed Bandit Tasks","date":"2025-05-15","arxiv_id":"2505.09901","repositories_listed":1,"syntology":null},{"url":"/paper/active-sampling-for-mri-based-sequential","slug":"active-sampling-for-mri-based-sequential","title":"Active Sampling for MRI-based Sequential Decision Making","date":"2025-05-07","arxiv_id":"2505.04586","repositories_listed":1,"syntology":null},{"url":"/paper/offline-dynamic-inventory-and-pricing","slug":"offline-dynamic-inventory-and-pricing","title":"Offline Dynamic Inventory and Pricing Strategy: Addressing Censored and Dependent Demand","date":"2025-04-14","arxiv_id":"2504.09831","repositories_listed":1,"syntology":null},{"url":"/paper/deep-reinforcement-learning-algorithms-for-1","slug":"deep-reinforcement-learning-algorithms-for-1","title":"Deep Reinforcement Learning Algorithms for Option Hedging","date":"2025-04-07","arxiv_id":"2504.05521","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-based-token-pruning-in","slug":"reinforcement-learning-based-token-pruning-in","title":"Reinforcement Learning-based Token Pruning in Vision Transformers: A Markov Game Approach","date":"2025-03-30","arxiv_id":"2503.23459","repositories_listed":1,"syntology":null},{"url":"/paper/towards-trustworthy-gui-agents-a-survey","slug":"towards-trustworthy-gui-agents-a-survey","title":"Towards Trustworthy GUI Agents: A Survey","date":"2025-03-30","arxiv_id":"2503.23434","repositories_listed":1,"syntology":null},{"url":"/paper/data-mixture-optimization-a-multi-fidelity","slug":"data-mixture-optimization-a-multi-fidelity","title":"Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework","date":"2025-03-26","arxiv_id":"2503.21023","repositories_listed":1,"syntology":null},{"url":"/paper/perspective-shifted-neuro-symbolic-world","slug":"perspective-shifted-neuro-symbolic-world","title":"Perspective-Shifted Neuro-Symbolic World Models: A Framework for Socially-Aware Robot Navigation","date":"2025-03-26","arxiv_id":"2503.20425","repositories_listed":1,"syntology":null},{"url":"/paper/depth-matters-multimodal-rgb-d-perception-for","slug":"depth-matters-multimodal-rgb-d-perception-for","title":"Depth Matters: Multimodal RGB-D Perception for Robust Autonomous Agents","date":"2025-03-20","arxiv_id":"2503.16711","repositories_listed":1,"syntology":null},{"url":"/paper/a-parallel-hybrid-action-space-reinforcement","slug":"a-parallel-hybrid-action-space-reinforcement","title":"A Parallel Hybrid Action Space Reinforcement Learning Model for Real-world Adaptive Traffic Signal Control","date":"2025-03-18","arxiv_id":"2503.14250","repositories_listed":1,"syntology":null},{"url":"/paper/quantization-free-autoregressive-action","slug":"quantization-free-autoregressive-action","title":"Quantization-Free Autoregressive Action Transformer","date":"2025-03-18","arxiv_id":"2503.14259","repositories_listed":1,"syntology":null},{"url":"/paper/locally-private-nonparametric-contextual","slug":"locally-private-nonparametric-contextual","title":"Locally Private Nonparametric Contextual Multi-armed Bandits","date":"2025-03-11","arxiv_id":"2503.08098","repositories_listed":1,"syntology":null},{"url":"/paper/on-generalization-across-environments-in","slug":"on-generalization-across-environments-in","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","date":"2025-03-02","arxiv_id":"2503.00799","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-combinatorial-1","slug":"reinforcement-learning-with-combinatorial-1","title":"Reinforcement learning with combinatorial actions for coupled restless bandits","date":"2025-03-01","arxiv_id":"2503.01919","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reinforcement-learning-with-combinatorial-1#ran","syntology_url":"https://syntology.ai/paper/2503.01919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01919"}},"official":{"repos":["lily-x/combinatorial-rmab"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scalable-decision-making-in-stochastic","slug":"scalable-decision-making-in-stochastic","title":"Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction","date":"2025-02-28","arxiv_id":"2502.21186","repositories_listed":1,"syntology":null},{"url":"/paper/wofostgym-a-crop-simulator-for-learning","slug":"wofostgym-a-crop-simulator-for-learning","title":"WOFOSTGym: A Crop Simulator for Learning Annual and Perennial Crop Management Strategies","date":"2025-02-26","arxiv_id":"2502.19308","repositories_listed":1,"syntology":null},{"url":"/paper/training-a-generally-curious-agent","slug":"training-a-generally-curious-agent","title":"Training a Generally Curious Agent","date":"2025-02-24","arxiv_id":"2502.17543","repositories_listed":1,"syntology":null},{"url":"/paper/pmat-optimizing-action-generation-order-in","slug":"pmat-optimizing-action-generation-order-in","title":"PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning","date":"2025-02-23","arxiv_id":"2502.16496","repositories_listed":1,"syntology":null},{"url":"/paper/alphamaze-enhancing-large-language-models","slug":"alphamaze-enhancing-large-language-models","title":"AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO","date":"2025-02-20","arxiv_id":"2502.14669","repositories_listed":1,"syntology":null},{"url":"/paper/making-universal-policies-universal","slug":"making-universal-policies-universal","title":"Making Universal Policies Universal","date":"2025-02-20","arxiv_id":"2502.14777","repositories_listed":1,"syntology":null},{"url":"/paper/value-gradient-sampler-sampling-as-sequential","slug":"value-gradient-sampler-sampling-as-sequential","title":"Value Gradient Sampler: Sampling as Sequential Decision Making","date":"2025-02-18","arxiv_id":"2502.13280","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-solve-the-min-max-mixed-shelves","slug":"learning-to-solve-the-min-max-mixed-shelves","title":"Learning to Solve the Min-Max Mixed-Shelves Picker-Routing Problem via Hierarchical and Parallel Decoding","date":"2025-02-14","arxiv_id":"2502.10233","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/learning-to-solve-the-min-max-mixed-shelves#ran","syntology_url":"https://syntology.ai/paper/2502.10233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10233"}},"official":{"repos":["ltluttmann/marl4msprp"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/plan-then-execute-an-empirical-study-of-user","slug":"plan-then-execute-an-empirical-study-of-user","title":"Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistant","date":"2025-02-03","arxiv_id":"2502.01390","repositories_listed":1,"syntology":null},{"url":"/paper/an-adaptable-budget-planner-for-enhancing","slug":"an-adaptable-budget-planner-for-enhancing","title":"An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising","date":"2025-01-26","arxiv_id":"2502.05187","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-inquiry-diagnosis-relationship","slug":"exploring-the-inquiry-diagnosis-relationship","title":"Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators","date":"2025-01-16","arxiv_id":"2501.09484","repositories_listed":1,"syntology":null},{"url":"/paper/on-learning-informative-trajectory-embeddings","slug":"on-learning-informative-trajectory-embeddings","title":"On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression","date":"2025-01-16","arxiv_id":"2501.09327","repositories_listed":1,"syntology":null},{"url":"/paper/co-activation-graph-analysis-of-safety","slug":"co-activation-graph-analysis-of-safety","title":"Co-Activation Graph Analysis of Safety-Verified and Explainable Deep Reinforcement Learning Policies","date":"2025-01-06","arxiv_id":"2501.03142","repositories_listed":1,"syntology":null},{"url":"/paper/minsstudio-a-streamlined-package-for","slug":"minsstudio-a-streamlined-package-for","title":"MineStudio: A Streamlined Package for Minecraft AI Agent Development","date":"2024-12-24","arxiv_id":"2412.18293","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/minsstudio-a-streamlined-package-for#ran","syntology_url":"https://syntology.ai/paper/2412.18293","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18293"}},"official":{"repos":["craftjarvis/minestudio"],"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/navigating-data-corruption-in-machine","slug":"navigating-data-corruption-in-machine","title":"Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies","date":"2024-12-24","arxiv_id":"2412.18296","repositories_listed":1,"syntology":null},{"url":"/paper/revelations-a-decidable-class-of-pomdps-with","slug":"revelations-a-decidable-class-of-pomdps-with","title":"Revelations: A Decidable Class of POMDPs with Omega-Regular Objectives","date":"2024-12-16","arxiv_id":"2412.12063","repositories_listed":1,"syntology":null},{"url":"/paper/how-should-we-represent-history-in","slug":"how-should-we-represent-history-in","title":"How Should We Represent History in Interpretable Models of Clinical Policies?","date":"2024-12-10","arxiv_id":"2412.07895","repositories_listed":1,"syntology":null},{"url":"/paper/discrete-time-distribution-steering-using","slug":"discrete-time-distribution-steering-using","title":"Discrete-Time Distribution Steering using Monte Carlo Tree Search","date":"2024-12-09","arxiv_id":"2412.06220","repositories_listed":1,"syntology":null},{"url":"/paper/nonmyopic-global-optimisation-via-approximate","slug":"nonmyopic-global-optimisation-via-approximate","title":"Nonmyopic Global Optimisation via Approximate Dynamic Programming","date":"2024-12-06","arxiv_id":"2412.04882","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/decision-transformer-vs-decision-mamba","slug":"decision-transformer-vs-decision-mamba","title":"Decision Transformer vs. Decision Mamba: Analysing the Complexity of Sequential Decision Making in Atari Games","date":"2024-12-01","arxiv_id":"2412.00725","repositories_listed":1,"syntology":null},{"url":"/paper/on-adaptivity-and-minimax-optimality-of-two","slug":"on-adaptivity-and-minimax-optimality-of-two","title":"On adaptivity and minimax optimality of two-sided nearest neighbors","date":"2024-11-20","arxiv_id":"2411.12965","repositories_listed":1,"syntology":null},{"url":"/paper/sandwich-towards-an-offline-differentiable","slug":"sandwich-towards-an-offline-differentiable","title":"SANDWICH: Towards an Offline, Differentiable, Fully-Trainable Wireless Neural Ray-Tracing Surrogate","date":"2024-11-13","arxiv_id":"2411.08767","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-control-of-mechanical-ventilators","slug":"optimal-control-of-mechanical-ventilators","title":"Optimal Control of Mechanical Ventilators with Learned Respiratory Dynamics","date":"2024-11-12","arxiv_id":"2411.07971","repositories_listed":1,"syntology":null},{"url":"/paper/pagerank-bandits-for-link-prediction","slug":"pagerank-bandits-for-link-prediction","title":"PageRank Bandits for Link Prediction","date":"2024-11-03","arxiv_id":"2411.01410","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pagerank-bandits-for-link-prediction#ran","syntology_url":"https://syntology.ai/paper/2411.01410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.01410"}},"official":{"repos":["jiaruzouu/prb"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/logicity-advancing-neuro-symbolic-ai-with","slug":"logicity-advancing-neuro-symbolic-ai-with","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","date":"2024-11-01","arxiv_id":"2411.00773","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/logicity-advancing-neuro-symbolic-ai-with#ran","syntology_url":"https://syntology.ai/paper/2411.00773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00773"}},"official":{"repos":["Jaraxxus-Me/LogiCity"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-versatile-skills-with-curriculum","slug":"learning-versatile-skills-with-curriculum","title":"Learning Versatile Skills with Curriculum Masking","date":"2024-10-23","arxiv_id":"2410.17744","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-versatile-skills-with-curriculum#ran","syntology_url":"https://syntology.ai/paper/2410.17744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17744"}},"official":{"repos":["yaotang23/currmask"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/counterfactual-effect-decomposition-in-multi","slug":"counterfactual-effect-decomposition-in-multi","title":"Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making","date":"2024-10-16","arxiv_id":"2410.12539","repositories_listed":1,"syntology":null},{"url":"/paper/dataenvgym-data-generation-agents-in-teacher","slug":"dataenvgym-data-generation-agents-in-teacher","title":"DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback","date":"2024-10-08","arxiv_id":"2410.06215","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dataenvgym-data-generation-agents-in-teacher#ran","syntology_url":"https://syntology.ai/paper/2410.06215","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06215"}},"official":{"repos":["codezakh/dataenvgym"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-a-fast-mixing-exogenous-block-mdp","slug":"learning-a-fast-mixing-exogenous-block-mdp","title":"Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory","date":"2024-10-03","arxiv_id":"2410.03016","repositories_listed":1,"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"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) · 5 unverified","sample_list":"/paper/learning-a-fast-mixing-exogenous-block-mdp#ran","syntology_url":"https://syntology.ai/paper/2410.03016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03016"}},"official":{"repos":["midi-lab/steel"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/adaptive-teachers-for-amortized-samplers","slug":"adaptive-teachers-for-amortized-samplers","title":"Adaptive teachers for amortized samplers","date":"2024-10-02","arxiv_id":"2410.01432","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":1,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adaptive-teachers-for-amortized-samplers#ran","syntology_url":"https://syntology.ai/paper/2410.01432","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01432"}},"official":{"repos":["alstn12088/adaptive-teacher"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/avid-adapting-video-diffusion-models-to-world","slug":"avid-adapting-video-diffusion-models-to-world","title":"AVID: Adapting Video Diffusion Models to World Models","date":"2024-10-01","arxiv_id":"2410.12822","repositories_listed":1,"syntology":null},{"url":"/paper/collaborative-comic-generation-integrating","slug":"collaborative-comic-generation-integrating","title":"Collaborative Comic Generation: Integrating Visual Narrative Theories with AI Models for Enhanced Creativity","date":"2024-09-25","arxiv_id":"2409.17263","repositories_listed":1,"syntology":null},{"url":"/paper/learning-discrete-world-models-for-heuristic","slug":"learning-discrete-world-models-for-heuristic","title":"Learning Discrete World Models for Heuristic Search","date":"2024-09-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/decentralized-cooperation-in-heterogeneous","slug":"decentralized-cooperation-in-heterogeneous","title":"Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards","date":"2024-08-12","arxiv_id":"2408.06503","repositories_listed":1,"syntology":null},{"url":"/paper/2408-03195","slug":"2408-03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","date":"2024-08-06","arxiv_id":"2408.03195","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":15,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/2408-03195#ran","syntology_url":"https://syntology.ai/paper/2408.03195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.03195"}},"official":{"repos":["JasonZhujp/RELIEF"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-00713","slug":"2408-00713","title":"Reinforcement Learning applied to Insurance Portfolio Pursuit","date":"2024-08-01","arxiv_id":"2408.00713","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-robust-decision-transformer","slug":"adversarial-robust-decision-transformer","title":"Adversarially Robust Decision Transformer","date":"2024-07-25","arxiv_id":"2407.18414","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":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/adversarial-robust-decision-transformer#ran","syntology_url":"https://syntology.ai/paper/2407.18414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18414"}},"official":{"repos":["xiaohangt/ardt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/reinforcement-learning-meets-visual-odometry","slug":"reinforcement-learning-meets-visual-odometry","title":"Reinforcement Learning Meets Visual Odometry","date":"2024-07-22","arxiv_id":"2407.15626","repositories_listed":1,"syntology":null},{"url":"/paper/preserving-the-privacy-of-reward-functions-in","slug":"preserving-the-privacy-of-reward-functions-in","title":"Preserving the Privacy of Reward Functions in MDPs through Deception","date":"2024-07-13","arxiv_id":"2407.09809","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/preserving-the-privacy-of-reward-functions-in#ran","syntology_url":"https://syntology.ai/paper/2407.09809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09809"}},"official":{"repos":["shshnkreddy/deceptiverl"],"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/long-term-fairness-in-sequential-multi-agent","slug":"long-term-fairness-in-sequential-multi-agent","title":"Long-Term Fairness in Sequential Multi-Agent Selection with Positive Reinforcement","date":"2024-07-10","arxiv_id":"2407.07350","repositories_listed":1,"syntology":null},{"url":"/paper/operator-world-models-for-reinforcement","slug":"operator-world-models-for-reinforcement","title":"Operator World Models for Reinforcement Learning","date":"2024-06-28","arxiv_id":"2406.19861","repositories_listed":1,"syntology":null},{"url":"/paper/instance-temperature-knowledge-distillation","slug":"instance-temperature-knowledge-distillation","title":"Instance Temperature Knowledge Distillation","date":"2024-06-27","arxiv_id":"2407.00115","repositories_listed":1,"syntology":null},{"url":"/paper/catastrophic-risk-aware-reinforcement","slug":"catastrophic-risk-aware-reinforcement","title":"Catastrophic-risk-aware reinforcement learning with extreme-value-theory-based policy gradients","date":"2024-06-21","arxiv_id":"2406.15612","repositories_listed":1,"syntology":null},{"url":"/paper/macrohft-memory-augmented-context-aware","slug":"macrohft-memory-augmented-context-aware","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","date":"2024-06-20","arxiv_id":"2406.14537","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":1,"n_honours":3,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/macrohft-memory-augmented-context-aware#ran","syntology_url":"https://syntology.ai/paper/2406.14537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14537"}},"official":{"repos":["ZONG0004/MacroHFT"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/give-me-an-example-like-this-episodic-active","slug":"give-me-an-example-like-this-episodic-active","title":"\"Give Me an Example Like This\": Episodic Active Reinforcement Learning from Demonstrations","date":"2024-06-05","arxiv_id":"2406.03069","repositories_listed":1,"syntology":null},{"url":"/paper/sound-heuristic-search-value-iteration-for","slug":"sound-heuristic-search-value-iteration-for","title":"Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives","date":"2024-06-05","arxiv_id":"2406.02871","repositories_listed":1,"syntology":null},{"url":"/paper/reflection-reinforced-self-training-for","slug":"reflection-reinforced-self-training-for","title":"Re-ReST: Reflection-Reinforced Self-Training for Language Agents","date":"2024-06-03","arxiv_id":"2406.01495","repositories_listed":1,"syntology":null}],"syntology_records":30,"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":107,"papers_where_code_ran_first_page":"/task/sequential-decision-making/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":13,"url":"/task/sequential-decision-making/papers/2","json":"/task/sequential-decision-making/papers/2.json","rows":100},{"order":"archive","page":3,"of":13,"url":"/task/sequential-decision-making/papers/3","json":"/task/sequential-decision-making/papers/3.json","rows":100},{"order":"archive","page":4,"of":13,"url":"/task/sequential-decision-making/papers/4","json":"/task/sequential-decision-making/papers/4.json","rows":100},{"order":"archive","page":5,"of":13,"url":"/task/sequential-decision-making/papers/5","json":"/task/sequential-decision-making/papers/5.json","rows":100},{"order":"archive","page":6,"of":13,"url":"/task/sequential-decision-making/papers/6","json":"/task/sequential-decision-making/papers/6.json","rows":100},{"order":"archive","page":7,"of":13,"url":"/task/sequential-decision-making/papers/7","json":"/task/sequential-decision-making/papers/7.json","rows":100},{"order":"archive","page":8,"of":13,"url":"/task/sequential-decision-making/papers/8","json":"/task/sequential-decision-making/papers/8.json","rows":100},{"order":"archive","page":9,"of":13,"url":"/task/sequential-decision-making/papers/9","json":"/task/sequential-decision-making/papers/9.json","rows":100},{"order":"archive","page":10,"of":13,"url":"/task/sequential-decision-making/papers/10","json":"/task/sequential-decision-making/papers/10.json","rows":100},{"order":"archive","page":11,"of":13,"url":"/task/sequential-decision-making/papers/11","json":"/task/sequential-decision-making/papers/11.json","rows":100},{"order":"archive","page":12,"of":13,"url":"/task/sequential-decision-making/papers/12","json":"/task/sequential-decision-making/papers/12.json","rows":100},{"order":"archive","page":13,"of":13,"url":"/task/sequential-decision-making/papers/13","json":"/task/sequential-decision-making/papers/13.json","rows":10},{"order":"ran","page":1,"of":2,"url":"/task/sequential-decision-making/papers/ran/1","json":"/task/sequential-decision-making/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":2,"url":"/task/sequential-decision-making/papers/ran/2","json":"/task/sequential-decision-making/papers/ran/2.json","rows":7}],"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":"891df62cc8585fc05b8528a9806e8979e998056797fbb6fff6906a3994612116","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}