{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/basepolicy","entry":"BasePolicy","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":8,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":10,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":10,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":4},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2605.21168","paper":"/paper/arxiv-2605-21168","title":"ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"QiyuRuan/ScenePilot","path":"safebench/scenario/scenario_policy/rl/scenepilot.py","file_url":"https://github.com/QiyuRuan/ScenePilot/blob/HEAD/safebench/scenario/scenario_policy/rl/scenepilot.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ac600ea2f467c8bc","mcp_get_code":{"code_sha256":"ac600ea2f467c8bc"}},{"arxiv_id":"2601.20765","paper":"/paper/arxiv-2601-20765","title":"LESS IS MORE: CLUSTERED CROSS-COVARIANCE CON-TROL FOR OFFLINE RL","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"NanMuZ/C4","path":"offlinerlkit/policy/model_free/c4cql.py","file_url":"https://github.com/NanMuZ/C4/blob/HEAD/offlinerlkit/policy/model_free/c4cql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f87ef2f5ecc1ce8e","mcp_get_code":{"code_sha256":"f87ef2f5ecc1ce8e"}},{"arxiv_id":"2404.04682","paper":"/paper/compositional-conservatism-a-transductive","title":"Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning","date":"2024-04-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"runamu/compositional-conservatism","path":"offlinerlkit/policy/model_free/divergent_policy.py","file_url":"https://github.com/runamu/compositional-conservatism/blob/HEAD/offlinerlkit/policy/model_free/divergent_policy.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"416a8b3131d89f0e","mcp_get_code":{"code_sha256":"416a8b3131d89f0e"}},{"arxiv_id":"2207.13081","paper":"/paper/future-dependent-value-based-off-policy-1","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","date":"2022-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aiueola/neurips2023-future-dependent-ope","path":"src/ope/value_based.py","file_url":"https://github.com/aiueola/neurips2023-future-dependent-ope/blob/HEAD/src/ope/value_based.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"626f06ce600233a5","mcp_get_code":{"code_sha256":"626f06ce600233a5"}},{"arxiv_id":"2206.04745","paper":"/paper/mildly-conservative-q-learning-for-offline","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","date":"2022-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihaosun1124/OfflineRL-Kit","path":"offlinerlkit/policy/model_free/mcq.py","file_url":"https://github.com/yihaosun1124/OfflineRL-Kit/blob/HEAD/offlinerlkit/policy/model_free/mcq.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"663ed93e901a35d7","mcp_get_code":{"code_sha256":"663ed93e901a35d7"}},{"arxiv_id":"2110.06169","paper":"/paper/offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihaosun1124/OfflineRL-Kit","path":"offlinerlkit/policy/model_free/iql.py","file_url":"https://github.com/yihaosun1124/OfflineRL-Kit/blob/HEAD/offlinerlkit/policy/model_free/iql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc6ec59a73ed3500","mcp_get_code":{"code_sha256":"bc6ec59a73ed3500"}},{"arxiv_id":"2110.06169","paper":"/paper/offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"typoverflow/OfflineRL-Lib","path":"offlinerllib/policy/model_free/iql.py","file_url":"https://github.com/typoverflow/OfflineRL-Lib/blob/HEAD/offlinerllib/policy/model_free/iql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f49a5596a23ec01c","mcp_get_code":{"code_sha256":"f49a5596a23ec01c"}},{"arxiv_id":"2110.06169","paper":"/paper/offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"runamu/compositional-conservatism","path":"offlinerlkit/policy/model_free/iql.py","file_url":"https://github.com/runamu/compositional-conservatism/blob/HEAD/offlinerlkit/policy/model_free/iql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c0883f7901f1f98","mcp_get_code":{"code_sha256":"7c0883f7901f1f98"}},{"arxiv_id":"2011.01928","paper":"/paper/generalization-to-new-actions-in-1","title":"Generalization to New Actions in Reinforcement Learning","date":"2020-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clvrai/new-actions-rl","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e8e8cf08b831157a","mcp_get_code":{"code_sha256":"e8e8cf08b831157a"}},{"arxiv_id":"1706.02275","paper":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Chan1998/MAAC","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"e3579cc107de4c0a","mcp_get_code":{"code_sha256":"e3579cc107de4c0a"}}]}