{"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/experiencereplay","entry":"ExperienceReplay","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":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":7,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"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":"2305.01381","paper":"/paper/sample-efficient-model-free-reinforcement-1","title":"Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees","date":"2023-05-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shaodaqian/rl-from-ltl","path":"algo/core.py","file_url":"https://github.com/shaodaqian/rl-from-ltl/blob/HEAD/algo/core.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4b68eac7ffda6ef","mcp_get_code":{"code_sha256":"b4b68eac7ffda6ef"}},{"arxiv_id":"1511.05952","paper":"/paper/prioritized-experience-replay","title":"Prioritized Experience Replay","date":"2015-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dtak/hip-mdp-public","path":"ExperienceReplay.py","file_url":"https://github.com/dtak/hip-mdp-public/blob/HEAD/ExperienceReplay.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"62c9777a79904b2f","mcp_get_code":{"code_sha256":"62c9777a79904b2f"}},{"arxiv_id":"1509.06461","paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daviddcho/supermario","path":"agent.py","file_url":"https://github.com/daviddcho/supermario/blob/HEAD/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"77c8ec6c865240fa","mcp_get_code":{"code_sha256":"77c8ec6c865240fa"}},{"arxiv_id":"1509.06461","paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hamishs/JAX-RL","path":"src/jax_rl/algorithms/dqn.py","file_url":"https://github.com/hamishs/JAX-RL/blob/HEAD/src/jax_rl/algorithms/dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"986cc90d7e4eeaf2","mcp_get_code":{"code_sha256":"986cc90d7e4eeaf2"}},{"arxiv_id":"1509.02971","paper":"/paper/continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JonasRSV/DDPG","path":"ddpg.py","file_url":"https://github.com/JonasRSV/DDPG/blob/HEAD/ddpg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e60542a6e12b3525","mcp_get_code":{"code_sha256":"e60542a6e12b3525"}},{"arxiv_id":"1312.5602","paper":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BH4/Deep-Reinforcement-Learning","path":"Training/qlearn.py","file_url":"https://github.com/BH4/Deep-Reinforcement-Learning/blob/HEAD/Training/qlearn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f9118b06dae7f603","mcp_get_code":{"code_sha256":"f9118b06dae7f603"}},{"arxiv_id":"1312.5602","paper":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JonasRSV/DQNTensorflow","path":"dqn.py","file_url":"https://github.com/JonasRSV/DQNTensorflow/blob/HEAD/dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"96164b4731db1134","mcp_get_code":{"code_sha256":"96164b4731db1134"}}]}