{"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/multiple-action-q-function","entry":"multiple_action_q_function","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":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":3,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":1},"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":"2502.05450","paper":"/paper/conrft-a-reinforced-fine-tuning-method-for","title":"ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy","date":"2025-02-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cccedric/conrft","path":"serl_launcher/serl_launcher/networks/actor_critic_nets.py","file_url":"https://github.com/cccedric/conrft/blob/HEAD/serl_launcher/serl_launcher/networks/actor_critic_nets.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":"c3ca7e8bfa98a6a6","mcp_get_code":{"code_sha256":"c3ca7e8bfa98a6a6"}},{"arxiv_id":"2405.05349","paper":"/paper/offline-model-based-optimization-via-policy","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","date":"2024-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yassineCh/PGS","path":"model.py","file_url":"https://github.com/yassineCh/PGS/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d06ff25d52ad20f5","mcp_get_code":{"code_sha256":"d06ff25d52ad20f5"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18c566cc009ddb07","mcp_get_code":{"code_sha256":"18c566cc009ddb07"}},{"arxiv_id":"2303.00957","paper":"/paper/preference-transformer-modeling-human","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","date":"2023-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"csmile-1006/preferencetransformer","path":"JaxPref/model.py","file_url":"https://github.com/csmile-1006/preferencetransformer/blob/HEAD/JaxPref/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18c566cc009ddb07","mcp_get_code":{"code_sha256":"18c566cc009ddb07"}},{"arxiv_id":"2301.12842","paper":"/paper/direct-preference-based-policy-optimization-1","title":"Direct Preference-based Policy Optimization without Reward Modeling","date":"2023-01-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"snu-mllab/DPPO","path":"JaxPref/model.py","file_url":"https://github.com/snu-mllab/DPPO/blob/HEAD/JaxPref/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18c566cc009ddb07","mcp_get_code":{"code_sha256":"18c566cc009ddb07"}},{"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/cql","path":"SimpleSAC/model.py","file_url":"https://github.com/young-geng/cql/blob/HEAD/SimpleSAC/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d06ff25d52ad20f5","mcp_get_code":{"code_sha256":"d06ff25d52ad20f5"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"18c566cc009ddb07","mcp_get_code":{"code_sha256":"18c566cc009ddb07"}}]}