{"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/ensembledcritic","entry":"EnsembledCritic","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":7,"n_papers_ran":7,"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":7,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":7,"unverified":0},"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":"2306.06569","paper":"/paper/policy-regularization-with-dataset-constraint","title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","date":"2023-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"prdc/prdc.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/prdc/prdc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2cd1bd32fbfa06a","mcp_get_code":{"code_sha256":"b2cd1bd32fbfa06a"}},{"arxiv_id":"2301.02328","paper":"/paper/extreme-q-learning-maxent-rl-without-entropy","title":"Extreme Q-Learning: MaxEnt RL without Entropy","date":"2023-01-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"eql/eql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/eql/eql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8f0d43f39f0d89d8","mcp_get_code":{"code_sha256":"8f0d43f39f0d89d8"}},{"arxiv_id":"2208.06193","paper":"/paper/diffusion-policies-as-an-expressive-policy","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","date":"2022-08-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"diffusion_ql/dql.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/diffusion_ql/dql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d6fcbdadf8cb4e3f","mcp_get_code":{"code_sha256":"d6fcbdadf8cb4e3f"}},{"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":"zzmtsvv/ORL","path":"mcq/mcq.py","file_url":"https://github.com/zzmtsvv/ORL/blob/HEAD/mcq/mcq.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3bc3e8876aab07e5","mcp_get_code":{"code_sha256":"3bc3e8876aab07e5"}},{"arxiv_id":"2110.01548","paper":"/paper/uncertainty-based-offline-reinforcement","title":"Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble","date":"2021-10-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"doge/doge.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/doge/doge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"31807722c6d0ebca","mcp_get_code":{"code_sha256":"31807722c6d0ebca"}},{"arxiv_id":"2006.09359","paper":"/paper/accelerating-online-reinforcement-learning","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"awac/awac.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/awac/awac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2bde489d14627922","mcp_get_code":{"code_sha256":"2bde489d14627922"}},{"arxiv_id":"1906.00949","paper":"/paper/190600949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","date":"2019-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zzmtsvv/rl_task","path":"bear/bear.py","file_url":"https://github.com/zzmtsvv/rl_task/blob/HEAD/bear/bear.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b68b870205409436","mcp_get_code":{"code_sha256":"b68b870205409436"}}]}