{"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/multi-objective-reinforcement-learning","name":"Multi-Objective Reinforcement Learning","slug":"multi-objective-reinforcement-learning","description_markdown":null,"categories":[{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":143,"papers_with_code":55,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)"}],"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":2,"rows_per_page":100,"shown":100,"of":143,"of_with_code":55,"tagged_in_all":143,"counts":{"archive_papers_tagged":143,"with_a_code_link":55,"where_syntology_ran_a_sample":19,"not_listed_spam_title":0,"listed":143,"listed_where_code_ran":19,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":19,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":19,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/optimization-of-molecules-via-deep","slug":"optimization-of-molecules-via-deep","title":"Optimization of Molecules via Deep Reinforcement Learning","date":"2018-10-19","arxiv_id":"1810.08678","repositories_listed":7,"syntology":null},{"url":"/paper/a-generalized-algorithm-for-multi-objective","slug":"a-generalized-algorithm-for-multi-objective","title":"A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation","date":"2019-08-21","arxiv_id":"1908.08342","repositories_listed":4,"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":2,"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/a-generalized-algorithm-for-multi-objective#ran","syntology_url":"https://syntology.ai/paper/1908.08342","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.08342"}},"official":{"repos":["RunzheYang/MORL"],"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":["listed","official"]}}},{"url":"/paper/sample-efficient-multi-objective-learning-via","slug":"sample-efficient-multi-objective-learning-via","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","date":"2023-01-18","arxiv_id":"2301.07784","repositories_listed":3,"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/sample-efficient-multi-objective-learning-via#ran","syntology_url":"https://syntology.ai/paper/2301.07784","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.07784"}},"official":{"repos":["lucasalegre/morl-baselines"],"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/dynamic-weights-in-multi-objective-deep","slug":"dynamic-weights-in-multi-objective-deep","title":"Dynamic Weights in Multi-Objective Deep Reinforcement Learning","date":"2018-09-20","arxiv_id":"1809.07803","repositories_listed":3,"syntology":null},{"url":"/paper/a-toolkit-for-reliable-benchmarking-and","slug":"a-toolkit-for-reliable-benchmarking-and","title":"A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning","date":"2023-09-26","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/mo-gym-a-library-of-multi-objective","slug":"mo-gym-a-library-of-multi-objective","title":"MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments","date":"2022-11-30","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/anchor-changing-regularized-natural-policy","slug":"anchor-changing-regularized-natural-policy","title":"Anchor-Changing Regularized Natural Policy Gradient for Multi-Objective Reinforcement Learning","date":"2022-06-10","arxiv_id":"2206.05357","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/anchor-changing-regularized-natural-policy#ran","syntology_url":"https://syntology.ai/paper/2206.05357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05357"}},"official":{"repos":["tliu1997/arnpg-morl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/prediction-guided-multi-objective","slug":"prediction-guided-multi-objective","title":"Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control","date":"2020-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/multi-objective-deep-reinforcement-learning","slug":"multi-objective-deep-reinforcement-learning","title":"Multi-Objective Deep Reinforcement Learning","date":"2016-10-09","arxiv_id":"1610.02707","repositories_listed":2,"syntology":null},{"url":"/paper/benchmarking-moeas-for-solving-continuous","slug":"benchmarking-moeas-for-solving-continuous","title":"Benchmarking MOEAs for solving continuous multi-objective RL problems","date":"2025-05-19","arxiv_id":"2505.13726","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/emorl-ensemble-multi-objective-reinforcement","slug":"emorl-ensemble-multi-objective-reinforcement","title":"EMORL: Ensemble Multi-Objective Reinforcement Learning for Efficient and Flexible LLM Fine-Tuning","date":"2025-05-05","arxiv_id":"2505.02579","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/mol-moe-training-preference-guided-routers","slug":"mol-moe-training-preference-guided-routers","title":"Mol-MoE: Training Preference-Guided Routers for Molecule Generation","date":"2025-02-08","arxiv_id":"2502.05633","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/mol-moe-training-preference-guided-routers#ran","syntology_url":"https://syntology.ai/paper/2502.05633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05633"}},"official":{"repos":["ddidacus/mol-moe"],"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/multi-objective-reinforcement-learning-for-2","slug":"multi-objective-reinforcement-learning-for-2","title":"Multi-Objective Reinforcement Learning for Power Grid Topology Control","date":"2025-01-27","arxiv_id":"2502.00040","repositories_listed":1,"syntology":null},{"url":"/paper/psmgd-periodic-stochastic-multi-gradient","slug":"psmgd-periodic-stochastic-multi-gradient","title":"PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization","date":"2024-12-14","arxiv_id":"2412.10961","repositories_listed":1,"syntology":null},{"url":"/paper/scalable-multi-objective-reinforcement","slug":"scalable-multi-objective-reinforcement","title":"Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance","date":"2024-11-27","arxiv_id":"2411.18195","repositories_listed":1,"syntology":null},{"url":"/paper/navigating-trade-offs-policy-summarization","slug":"navigating-trade-offs-policy-summarization","title":"Navigating Trade-offs: Policy Summarization for Multi-Objective Reinforcement Learning","date":"2024-11-07","arxiv_id":"2411.04784","repositories_listed":1,"syntology":null},{"url":"/paper/c-morl-multi-objective-reinforcement-learning","slug":"c-morl-multi-objective-reinforcement-learning","title":"C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front","date":"2024-10-03","arxiv_id":"2410.02236","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/c-morl-multi-objective-reinforcement-learning#ran","syntology_url":"https://syntology.ai/paper/2410.02236","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02236"}},"official":{"repos":["ruohliuq/c-morl"],"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/inferring-preferences-from-demonstrations-in-2","slug":"inferring-preferences-from-demonstrations-in-2","title":"Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning","date":"2024-09-30","arxiv_id":"2409.20258","repositories_listed":1,"syntology":null},{"url":"/paper/stage-wise-reward-shaping-for-acrobatic","slug":"stage-wise-reward-shaping-for-acrobatic","title":"Stage-Wise Reward Shaping for Acrobatic Robots: A Constrained Multi-Objective Reinforcement Learning Approach","date":"2024-09-24","arxiv_id":"2409.15755","repositories_listed":1,"syntology":null},{"url":"/paper/learning-pareto-set-for-multi-objective","slug":"learning-pareto-set-for-multi-objective","title":"Learning Pareto Set for Multi-Objective Continuous Robot Control","date":"2024-06-27","arxiv_id":"2406.18924","repositories_listed":1,"syntology":null},{"url":"/paper/the-max-min-formulation-of-multi-objective","slug":"the-max-min-formulation-of-multi-objective","title":"The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm","date":"2024-06-12","arxiv_id":"2406.07826","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-max-min-formulation-of-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2406.07826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07826"}},"official":{"repos":["giseung-park/maxmin-morl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-objective-reinforcement-learning-from","slug":"multi-objective-reinforcement-learning-from","title":"Multi-objective Reinforcement learning from AI Feedback","date":"2024-06-11","arxiv_id":"2406.07295","repositories_listed":1,"syntology":null},{"url":"/paper/deep-multi-objective-reinforcement-learning","slug":"deep-multi-objective-reinforcement-learning","title":"Deep Multi-Objective Reinforcement Learning for Utility-Based Infrastructural Maintenance Optimization","date":"2024-06-10","arxiv_id":"2406.06184","repositories_listed":1,"syntology":null},{"url":"/paper/spatio-temporal-early-prediction-based-on","slug":"spatio-temporal-early-prediction-based-on","title":"STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning","date":"2024-06-06","arxiv_id":"2406.04035","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spatio-temporal-early-prediction-based-on#ran","syntology_url":"https://syntology.ai/paper/2406.04035","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04035"}},"official":{"repos":["coco0106/MO-STEP"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/safe-and-balanced-a-framework-for-constrained","slug":"safe-and-balanced-a-framework-for-constrained","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","date":"2024-05-26","arxiv_id":"2405.16390","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":1,"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/safe-and-balanced-a-framework-for-constrained#ran","syntology_url":"https://syntology.ai/paper/2405.16390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.16390"}},"official":{"repos":["SafeRL-Lab/Safe-Multi-Objective-MuJoCo"],"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/ucb-driven-utility-function-search-for-multi","slug":"ucb-driven-utility-function-search-for-multi","title":"UCB-driven Utility Function Search for Multi-objective Reinforcement Learning","date":"2024-05-01","arxiv_id":"2405.00410","repositories_listed":1,"syntology":null},{"url":"/paper/reinforcement-learning-with-dynamic-multi","slug":"reinforcement-learning-with-dynamic-multi","title":"Dynamic Multi-Reward Weighting for Multi-Style Controllable Generation","date":"2024-02-21","arxiv_id":"2402.14146","repositories_listed":1,"syntology":null},{"url":"/paper/divide-and-conquer-provably-unveiling-the","slug":"divide-and-conquer-provably-unveiling-the","title":"Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning","date":"2024-02-11","arxiv_id":"2402.07182","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":5,"n_instrument":11,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":17,"phrase":"16 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; 11 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/divide-and-conquer-provably-unveiling-the#ran","syntology_url":"https://syntology.ai/paper/2402.07182","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07182"}},"official":{"repos":["wilrop/ipro"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/policy-regularized-offline-multi-objective","slug":"policy-regularized-offline-multi-objective","title":"Policy-regularized Offline Multi-objective Reinforcement Learning","date":"2024-01-04","arxiv_id":"2401.02244","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/policy-regularized-offline-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2401.02244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.02244"}},"official":{"repos":["qianlin04/prmorl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/promptable-behaviors-personalizing-multi","slug":"promptable-behaviors-personalizing-multi","title":"Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences","date":"2023-12-14","arxiv_id":"2312.09337","repositories_listed":1,"syntology":null},{"url":"/paper/adsorbrl-deep-multi-objective-reinforcement","slug":"adsorbrl-deep-multi-objective-reinforcement","title":"AdsorbRL: Deep Multi-Objective Reinforcement Learning for Inverse Catalysts Design","date":"2023-12-04","arxiv_id":"2312.02308","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":1,"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/adsorbrl-deep-multi-objective-reinforcement#ran","syntology_url":"https://syntology.ai/paper/2312.02308","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02308"}},"official":{"repos":["rlacombe/adsorbrl"],"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/multi-objective-reinforcement-learning-based-2","slug":"multi-objective-reinforcement-learning-based-2","title":"Multi-Objective Reinforcement Learning Based on Decomposition: A Taxonomy and Framework","date":"2023-11-21","arxiv_id":"2311.12495","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":12,"n_pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/multi-objective-reinforcement-learning-based-2#ran","syntology_url":"https://syntology.ai/paper/2311.12495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12495"}},"official":{"repos":["lucasalegre/morl-baselines"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hyperparameter-optimization-for-multi","slug":"hyperparameter-optimization-for-multi","title":"Hyperparameter Optimization for Multi-Objective Reinforcement Learning","date":"2023-10-25","arxiv_id":"2310.16487","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-soups-personalized-large","slug":"personalized-soups-personalized-large","title":"Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging","date":"2023-10-17","arxiv_id":"2310.11564","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":15,"phrase":"13 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; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/personalized-soups-personalized-large#ran","syntology_url":"https://syntology.ai/paper/2310.11564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11564"}},"official":{"repos":["joeljang/rlphf"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/gmocat-a-graph-enhanced-multi-objective","slug":"gmocat-a-graph-enhanced-multi-objective","title":"GMOCAT: A Graph-Enhanced Multi-Objective Method for Computerized Adaptive Testing","date":"2023-10-11","arxiv_id":"2310.07477","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gmocat-a-graph-enhanced-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2310.07477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07477"}},"official":{"repos":["justarter/gmocat"],"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","unlocated"]}}},{"url":"/paper/distributional-pareto-optimal-multi-objective","slug":"distributional-pareto-optimal-multi-objective","title":"Distributional Pareto-Optimal Multi-Objective Reinforcement Learning","date":"2023-09-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scaling-pareto-efficient-decision-making-via","slug":"scaling-pareto-efficient-decision-making-via","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","date":"2023-04-30","arxiv_id":"2305.00567","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scaling-pareto-efficient-decision-making-via#ran","syntology_url":"https://syntology.ai/paper/2305.00567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00567"}},"official":{"repos":["baitingzbt/peda"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/piecewise-stationary-multi-objective-multi","slug":"piecewise-stationary-multi-objective-multi","title":"Piecewise-Stationary Multi-Objective Multi-Armed Bandit with Application to Joint Communications and Sensing","date":"2023-02-10","arxiv_id":"2302.05257","repositories_listed":1,"syntology":null},{"url":"/paper/lexicographic-multi-objective-reinforcement","slug":"lexicographic-multi-objective-reinforcement","title":"Lexicographic Multi-Objective Reinforcement Learning","date":"2022-12-28","arxiv_id":"2212.13769","repositories_listed":1,"syntology":null},{"url":"/paper/q-pensieve-boosting-sample-efficiency-of","slug":"q-pensieve-boosting-sample-efficiency-of","title":"Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots","date":"2022-12-06","arxiv_id":"2212.03117","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/q-pensieve-boosting-sample-efficiency-of#ran","syntology_url":"https://syntology.ai/paper/2212.03117","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.03117"}},"official":{"repos":["NYCU-RL-Bandits-Lab/Q-Pensieve"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/welfare-and-fairness-in-multi-objective","slug":"welfare-and-fairness-in-multi-objective","title":"Welfare and Fairness in Multi-objective Reinforcement Learning","date":"2022-11-30","arxiv_id":"2212.01382","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/welfare-and-fairness-in-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2212.01382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.01382"}},"official":{"repos":["MuhangTian/Fair-MORL-AAMAS"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/get-it-in-writing-formal-contracts-mitigate","slug":"get-it-in-writing-formal-contracts-mitigate","title":"Formal Contracts Mitigate Social Dilemmas in Multi-Agent RL","date":"2022-08-22","arxiv_id":"2208.10469","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/get-it-in-writing-formal-contracts-mitigate#ran","syntology_url":"https://syntology.ai/paper/2208.10469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10469"}},"official":{"repos":["algorithmic-alignment-lab/contracts"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/pd-morl-preference-driven-multi-objective","slug":"pd-morl-preference-driven-multi-objective","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","date":"2022-08-16","arxiv_id":"2208.07914","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"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 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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/pd-morl-preference-driven-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2208.07914","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.07914"}},"official":{"repos":["tbasaklar/PDMORL-Preference-Driven-Multi-Objective-Reinforcement-Learning-Algorithm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/gtlo-a-generalized-and-non-linear-multi","slug":"gtlo-a-generalized-and-non-linear-multi","title":"gTLO: A Generalized and Non-linear Multi-Objective Deep Reinforcement Learning Approach","date":"2022-04-11","arxiv_id":"2204.04988","repositories_listed":1,"syntology":null},{"url":"/paper/pareto-conditioned-networks","slug":"pareto-conditioned-networks","title":"Pareto Conditioned Networks","date":"2022-04-11","arxiv_id":"2204.05036","repositories_listed":1,"syntology":null},{"url":"/paper/skill-based-multi-objective-reinforcement","slug":"skill-based-multi-objective-reinforcement","title":"Skill-based Multi-objective Reinforcement Learning of Industrial Robot Tasks with Planning and Knowledge Integration","date":"2022-03-18","arxiv_id":"2203.10033","repositories_listed":1,"syntology":null},{"url":"/paper/a-review-of-the-deep-sea-treasure-problem-as","slug":"a-review-of-the-deep-sea-treasure-problem-as","title":"A Review of the Deep Sea Treasure problem as a Multi-Objective Reinforcement Learning Benchmark","date":"2021-10-13","arxiv_id":"2110.06742","repositories_listed":1,"syntology":null},{"url":"/paper/a-practical-guide-to-multi-objective","slug":"a-practical-guide-to-multi-objective","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","date":"2021-03-17","arxiv_id":"2103.09568","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-impact-of-tunable-agents-in","slug":"exploring-the-impact-of-tunable-agents-in","title":"Exploring the Impact of Tunable Agents in Sequential Social Dilemmas","date":"2021-01-28","arxiv_id":"2101.11967","repositories_listed":1,"syntology":null},{"url":"/paper/accommodating-picky-customers-regret-bound","slug":"accommodating-picky-customers-regret-bound","title":"Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning","date":"2020-11-25","arxiv_id":"2011.13034","repositories_listed":1,"syntology":null},{"url":"/paper/collision-avoidance-robotics-via-meta","slug":"collision-avoidance-robotics-via-meta","title":"Collision Avoidance Robotics Via Meta-Learning (CARML)","date":"2020-07-16","arxiv_id":"2007.08616","repositories_listed":1,"syntology":null},{"url":"/paper/a-distributional-view-on-multi-objective","slug":"a-distributional-view-on-multi-objective","title":"A Distributional View on Multi-Objective Policy Optimization","date":"2020-05-15","arxiv_id":"2005.07513","repositories_listed":1,"syntology":null},{"url":"/paper/predicting-optimal-value-functions-by","slug":"predicting-optimal-value-functions-by","title":"Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning","date":"2019-09-11","arxiv_id":"1909.05004","repositories_listed":1,"syntology":null},{"url":null,"slug":"multi-objective-reinforcement-learning-for-6","title":"Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management","date":"2025-06-25","arxiv_id":"2506.20853","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-preference-multi-objective","title":"Dynamic Preference Multi-Objective Reinforcement Learning for Internet Network Management","date":"2025-06-16","arxiv_id":"2506.13153","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairdice-fairness-driven-offline-multi","title":"FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning","date":"2025-06-09","arxiv_id":"2506.08062","repositories_listed":0,"syntology":null},{"url":null,"slug":"2505-10803","title":"Developing and Integrating Trust Modeling into Multi-Objective Reinforcement Learning for Intelligent Agricultural Management","date":"2025-05-16","arxiv_id":"2505.10803","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-reinforcement-learning-for-5","title":"Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control","date":"2025-05-12","arxiv_id":"2505.07607","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-reinforcement-learning-for-4","title":"Multi-Objective Reinforcement Learning for Adaptive Personalized Autonomous Driving","date":"2025-05-08","arxiv_id":"2505.05223","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-multi-objective-reinforcement","title":"A Novel Multi-Objective Reinforcement Learning Algorithm for Pursuit-Evasion Game","date":"2025-03-09","arxiv_id":"2503.06741","repositories_listed":0,"syntology":null},{"url":null,"slug":"closing-the-intent-to-reality-gap-via","title":"Closing the Intent-to-Behavior Gap via Fulfillment Priority Logic","date":"2025-03-04","arxiv_id":"2503.05818","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-reinforcement-learning-for-3","title":"Multi-Objective Reinforcement Learning for Critical Scenario Generation of Autonomous Vehicles","date":"2025-02-18","arxiv_id":"2502.15792","repositories_listed":0,"syntology":null},{"url":null,"slug":"bone-soups-a-seek-and-soup-model-merging","title":"Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation","date":"2025-02-15","arxiv_id":"2502.10762","repositories_listed":0,"syntology":null},{"url":null,"slug":"aerial-reliable-collaborative-communications","title":"Aerial Reliable Collaborative Communications for Terrestrial Mobile Users via Evolutionary Multi-Objective Deep Reinforcement Learning","date":"2025-02-09","arxiv_id":"2502.05824","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-multi-objective","title":"Towards Efficient Multi-Objective Optimisation for Real-World Power Grid Topology Control","date":"2025-01-24","arxiv_id":"2502.00034","repositories_listed":0,"syntology":null},{"url":null,"slug":"pareto-set-learning-for-multi-objective","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","date":"2025-01-12","arxiv_id":"2501.06773","repositories_listed":0,"syntology":null},{"url":null,"slug":"radiology-report-generation-via-multi","title":"Radiology Report Generation via Multi-objective Preference Optimization","date":"2024-12-12","arxiv_id":"2412.08901","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-alignment-dynamic-preference","title":"Adaptive Alignment: Dynamic Preference Adjustments via Multi-Objective Reinforcement Learning for Pluralistic AI","date":"2024-10-31","arxiv_id":"2410.23630","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-objective-reinforcement-learning-a-tool","title":"Multi-objective Reinforcement Learning: A Tool for Pluralistic Alignment","date":"2024-10-15","arxiv_id":"2410.11221","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-offline-adaptation-framework-for","title":"An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning","date":"2024-09-16","arxiv_id":"2409.09958","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-models-as-efficient-reward","title":"Large Language Models as Efficient Reward Function Searchers for Custom-Environment Multi-Objective Reinforcement Learning","date":"2024-09-04","arxiv_id":"2409.02428","repositories_listed":0,"syntology":null},{"url":null,"slug":"moduli-unlocking-preference-generalization","title":"MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning","date":"2024-08-28","arxiv_id":"2408.15501","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-01188","title":"Multi-Objective Deep Reinforcement Learning for Optimisation in Autonomous Systems","date":"2024-08-02","arxiv_id":"2408.01188","repositories_listed":0,"syntology":null},{"url":null,"slug":"traversing-pareto-optimal-policies-provably","title":"Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning","date":"2024-07-24","arxiv_id":"2407.17466","repositories_listed":0,"syntology":null},{"url":null,"slug":"in-search-for-architectures-and-loss","title":"In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning","date":"2024-07-23","arxiv_id":"2407.16807","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-meta-learning-approach-for-multi-objective","title":"A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments","date":"2024-07-16","arxiv_id":"2407.11489","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-pareto-optimal-decision-making-for","title":"Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference","date":"2024-06-17","arxiv_id":"2406.11984","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-dimensional-optimization-for-text","title":"Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning","date":"2024-06-01","arxiv_id":"2406.00303","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-vehicular-networks-with","title":"Optimizing Vehicular Networks with Variational Quantum Circuits-based Reinforcement Learning","date":"2024-05-29","arxiv_id":"2405.18984","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-time-analysis-for-conflict-avoidant","title":"Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning","date":"2024-05-25","arxiv_id":"2405.16077","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-multi-objective-reinforcement","title":"Generalized Multi-Objective Reinforcement Learning with Envelope Updates in URLLC-enabled Vehicular Networks","date":"2024-05-18","arxiv_id":"2405.11331","repositories_listed":0,"syntology":null},{"url":null,"slug":"finite-time-convergence-and-sample-complexity-1","title":"Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning","date":"2024-05-05","arxiv_id":"2405.03082","repositories_listed":0,"syntology":null},{"url":null,"slug":"demonstration-guided-multi-objective","title":"Demonstration Guided Multi-Objective Reinforcement Learning","date":"2024-04-05","arxiv_id":"2404.03997","repositories_listed":0,"syntology":null},{"url":null,"slug":"scale-invariant-gradient-aggregation-for","title":"Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning","date":"2024-03-01","arxiv_id":"2403.00282","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-centric-aware-uav-trajectory-planning","title":"Human-Centric Aware UAV Trajectory Planning in Search and Rescue Missions Employing Multi-Objective Reinforcement Learning with AHP and Similarity-Based Experience Replay","date":"2024-02-28","arxiv_id":"2402.18487","repositories_listed":0,"syntology":null},{"url":null,"slug":"morl-prompt-an-empirical-analysis-of-multi","title":"MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimization","date":"2024-02-18","arxiv_id":"2402.11711","repositories_listed":0,"syntology":null},{"url":null,"slug":"surpassing-legacy-approaches-and-human","title":"Surpassing legacy approaches to PWR core reload optimization with single-objective Reinforcement learning","date":"2024-02-16","arxiv_id":"2402.11040","repositories_listed":0,"syntology":null},{"url":null,"slug":"pmgda-a-preference-based-multiple-gradient","title":"PMGDA: A Preference-based Multiple Gradient Descent Algorithm","date":"2024-02-14","arxiv_id":"2402.09492","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-function-interference-and-greedy-action","title":"Value function interference and greedy action selection in value-based multi-objective reinforcement learning","date":"2024-02-09","arxiv_id":"2402.06266","repositories_listed":0,"syntology":null},{"url":null,"slug":"utility-based-reinforcement-learning-unifying","title":"Utility-Based Reinforcement Learning: Unifying Single-objective and Multi-objective Reinforcement Learning","date":"2024-02-05","arxiv_id":"2402.02665","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-and-optimization-of-epidemiological","title":"Modeling and Optimization of Epidemiological Control Policies Through Reinforcement Learning","date":"2024-01-25","arxiv_id":"2402.06640","repositories_listed":0,"syntology":null},{"url":null,"slug":"inferring-preferences-from-demonstrations-in-1","title":"Inferring Preferences from Demonstrations in Multi-Objective Residential Energy Management","date":"2024-01-15","arxiv_id":"2401.07722","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-investigation-of-value-based","title":"An Empirical Investigation of Value-Based Multi-objective Reinforcement Learning for Stochastic Environments","date":"2024-01-06","arxiv_id":"2401.03163","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-in-the-loop-policy-optimization-for","title":"Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning","date":"2024-01-04","arxiv_id":"2401.02160","repositories_listed":0,"syntology":null},{"url":null,"slug":"pareto-envelope-augmented-with-reinforcement","title":"Multi-Objective Reinforcement Learning-based Approach for Pressurized Water Reactor Optimization","date":"2023-12-15","arxiv_id":"2312.10194","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-robotic-navigation-an-evaluation-of","title":"Enhancing Robotic Navigation: An Evaluation of Single and Multi-Objective Reinforcement Learning Strategies","date":"2023-12-13","arxiv_id":"2312.07953","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonlinear-multi-objective-reinforcement","title":"Multi-objective Reinforcement Learning with Nonlinear Preferences: Provable Approximation for Maximizing Expected Scalarized Return","date":"2023-11-05","arxiv_id":"2311.02544","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlled-decoding-from-language-models","title":"Controlled Decoding from Language Models","date":"2023-10-25","arxiv_id":"2310.17022","repositories_listed":0,"syntology":null}],"syntology_records":19,"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":19,"papers_where_code_ran_first_page":"/task/multi-objective-reinforcement-learning/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":2,"url":"/task/multi-objective-reinforcement-learning/papers/2","json":"/task/multi-objective-reinforcement-learning/papers/2.json","rows":43},{"order":"ran","page":1,"of":1,"url":"/task/multi-objective-reinforcement-learning/papers/ran/1","json":"/task/multi-objective-reinforcement-learning/papers/ran/1.json","rows":19}],"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":"0aca234a25038a525f57b8e8677ef5155cf937c28da61d7b4d3818e6e3510746","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}