{"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/update-target-network","entry":"update_target_network","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":0,"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":0,"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":0,"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":"2410.18076","paper":"/paper/leveraging-skills-from-unlabeled-prior-data","title":"Leveraging Skills from Unlabeled Prior Data for Efficient Online Exploration","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rail-berkeley/supe","path":"supe/agents/model.py","file_url":"https://github.com/rail-berkeley/supe/blob/HEAD/supe/agents/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f23c0c9faf00d830","mcp_get_code":{"code_sha256":"f23c0c9faf00d830"}},{"arxiv_id":"2310.17966","paper":"/paper/train-once-get-a-family-state-adaptive-1","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","date":"2023-10-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeapLabTHU/FamO2O","path":"jax_cql/JaxCQL/model.py","file_url":"https://github.com/LeapLabTHU/FamO2O/blob/HEAD/jax_cql/JaxCQL/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f23c0c9faf00d830","mcp_get_code":{"code_sha256":"f23c0c9faf00d830"}},{"arxiv_id":"2310.08558","paper":"/paper/offline-retraining-for-online-rl-decoupled","title":"Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MaxSobolMark/OOO","path":"OOO_for_calql/model.py","file_url":"https://github.com/MaxSobolMark/OOO/blob/HEAD/OOO_for_calql/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f23c0c9faf00d830","mcp_get_code":{"code_sha256":"f23c0c9faf00d830"}},{"arxiv_id":"2210.07484","paper":"/paper/mutual-information-regularized-offline-1","title":"Mutual Information Regularized Offline Reinforcement Learning","date":"2022-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/MISA","path":"algos/model.py","file_url":"https://github.com/sail-sg/MISA/blob/HEAD/algos/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"528710698bd3cfc6","mcp_get_code":{"code_sha256":"528710698bd3cfc6"}},{"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":"young-geng/jaxcql","path":"JaxCQL/model.py","file_url":"https://github.com/young-geng/jaxcql/blob/HEAD/JaxCQL/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f23c0c9faf00d830","mcp_get_code":{"code_sha256":"f23c0c9faf00d830"}}]}