{"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/policy-evaluation","entry":"policy_evaluation","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":6,"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":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":2,"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":"2602.10793","paper":"/paper/arxiv-2602-10793","title":"Semi-Supervised Cross-Domain Imitation Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"JasonMa2016/SMODICE","path":"smodice_tabular/utils.py","file_url":"https://github.com/JasonMa2016/SMODICE/blob/HEAD/smodice_tabular/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9ceec323249d2b9","mcp_get_code":{"code_sha256":"f9ceec323249d2b9"}},{"arxiv_id":"2408.05342","paper":"/paper/optimal-treatment-allocation-strategies-for-a","title":"ARMA-Design: Optimal Treatment Allocation Strategies for A/B Testing in Partially Observable Time Series Experiments","date":"2024-08-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"datake/armadesign","path":"ARMAdesign.py","file_url":"https://github.com/datake/armadesign/blob/HEAD/ARMAdesign.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c83115cee3644846","mcp_get_code":{"code_sha256":"c83115cee3644846"}},{"arxiv_id":"2406.12284","paper":"/paper/demystifying-the-recency-heuristic-in","title":"Demystifying the Recency Heuristic in Temporal-Difference Learning","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"brett-daley/recency-heuristic","path":"learning/dynamic_programming.py","file_url":"https://github.com/brett-daley/recency-heuristic/blob/HEAD/learning/dynamic_programming.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"202dd22e01f0f721","mcp_get_code":{"code_sha256":"202dd22e01f0f721"}},{"arxiv_id":"2405.17477","paper":"/paper/ollie-imitation-learning-from-offline","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"secury/optidice","path":"mdp.py","file_url":"https://github.com/secury/optidice/blob/HEAD/mdp.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9ceec323249d2b9","mcp_get_code":{"code_sha256":"f9ceec323249d2b9"}},{"arxiv_id":"2207.08645","paper":"/paper/active-exploration-for-inverse-reinforcement","title":"Active Exploration for Inverse Reinforcement Learning","date":"2022-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lasgroup/aceirl","path":"src/active_irl/aceirl/algorithm.py","file_url":"https://github.com/lasgroup/aceirl/blob/HEAD/src/active_irl/aceirl/algorithm.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2a38774ec59331df","mcp_get_code":{"code_sha256":"2a38774ec59331df"}},{"arxiv_id":"2204.08957","paper":"/paper/coptidice-offline-constrained-reinforcement-1","title":"COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation","date":"2022-04-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepmind/constrained_optidice","path":"tabular/mdp_util.py","file_url":"https://github.com/deepmind/constrained_optidice/blob/HEAD/tabular/mdp_util.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":"77a7c8ddd9479170","mcp_get_code":{"code_sha256":"77a7c8ddd9479170"}}]}