{"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/sacpolicy","entry":"SACPolicy","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":5,"n_papers_ran":3,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"unverified":2},"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":"2603.08118","paper":"/paper/arxiv-2603-08118","title":"Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting","date":"2026-03-09","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"zq2r/ROMI","path":"offlinerlkit/policy/model_based/romi.py","file_url":"https://github.com/zq2r/ROMI/blob/HEAD/offlinerlkit/policy/model_based/romi.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"77f178161afd213f","mcp_get_code":{"code_sha256":"77f178161afd213f"}},{"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":"5445ab0c0a06b738","mcp_get_code":{"code_sha256":"5445ab0c0a06b738"}},{"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":"a48659302894ea24","mcp_get_code":{"code_sha256":"a48659302894ea24"}},{"arxiv_id":"2006.04779","paper":"/paper/conservative-q-learning-for-offline","title":"Conservative Q-Learning for Offline Reinforcement Learning","date":"2020-06-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"runamu/compositional-conservatism","path":"offlinerlkit/policy/model_free/cql.py","file_url":"https://github.com/runamu/compositional-conservatism/blob/HEAD/offlinerlkit/policy/model_free/cql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3487f84da3586b8f","mcp_get_code":{"code_sha256":"3487f84da3586b8f"}},{"arxiv_id":"2005.13239","paper":"/paper/mopo-model-based-offline-policy-optimization","title":"MOPO: Model-based Offline Policy Optimization","date":"2020-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yihaosun1124/OfflineRL-Kit","path":"offlinerlkit/policy/model_based/mopo.py","file_url":"https://github.com/yihaosun1124/OfflineRL-Kit/blob/HEAD/offlinerlkit/policy/model_based/mopo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b3d37324c880e711","mcp_get_code":{"code_sha256":"b3d37324c880e711"}}]}