{"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/get-flat-params","entry":"get_flat_params","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":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":2,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2608.02332","paper":"/paper/arxiv-2608-02332","title":"Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"aviralkumar2907/CQL","path":"d4rl/rlkit/core/batch_rl_algorithm.py","file_url":"https://github.com/aviralkumar2907/CQL/blob/HEAD/d4rl/rlkit/core/batch_rl_algorithm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b9a51e3e3be7a6e","mcp_get_code":{"code_sha256":"9b9a51e3e3be7a6e"}},{"arxiv_id":"2605.14779","paper":"/paper/arxiv-2605-14779","title":"PENG'S Q(λ) FOR CONSERVATIVE VALUE ESTIMATION IN OFFLINE REINFORCEMENT LEARNING","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"hyeon1996/EPQ","path":"rlkit/core/batch_rl_algorithm.py","file_url":"https://github.com/hyeon1996/EPQ/blob/HEAD/rlkit/core/batch_rl_algorithm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9b9a51e3e3be7a6e","mcp_get_code":{"code_sha256":"9b9a51e3e3be7a6e"}},{"arxiv_id":"2311.05067","paper":"/paper/accelerating-exploration-with-unlabeled-prior-1","title":"Accelerating Exploration with Unlabeled Prior Data","date":"2023-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"avisingh599/cog","path":"rlkit/core/batch_rl_algorithm.py","file_url":"https://github.com/avisingh599/cog/blob/HEAD/rlkit/core/batch_rl_algorithm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9b9a51e3e3be7a6e","mcp_get_code":{"code_sha256":"9b9a51e3e3be7a6e"}},{"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":"ikostrikov/cql-results","path":"d4rl/rlkit/core/batch_rl_algorithm.py","file_url":"https://github.com/ikostrikov/cql-results/blob/HEAD/d4rl/rlkit/core/batch_rl_algorithm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"9b9a51e3e3be7a6e","mcp_get_code":{"code_sha256":"9b9a51e3e3be7a6e"}},{"arxiv_id":"1705.10528","paper":"/paper/constrained-policy-optimization","title":"Constrained Policy Optimization","date":"2017-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Bigpig4396/PyTorch-Constrained-Policy-Optimization-CPO","path":"CPO.py","file_url":"https://github.com/Bigpig4396/PyTorch-Constrained-Policy-Optimization-CPO/blob/HEAD/CPO.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f0d38d6259a00367","mcp_get_code":{"code_sha256":"f0d38d6259a00367"}}]}