{"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/dqn","entry":"DQN","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":8,"n_papers_ran":4,"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":23,"n_samples_ran":13,"n_samples_fingerprinted":3,"n_places":23,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":13,"unverified":10},"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":"2606.20832","paper":"/paper/arxiv-2606-20832","title":"ReLaTS: a Reinforcement Learning-based method for dynamically determining the coupling Time Step in multi-scale simulations of self-gravitating systems","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"veronicasaz/RL_bridgedCluster","path":"TrainRL.py","file_url":"https://github.com/veronicasaz/RL_bridgedCluster/blob/HEAD/TrainRL.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a2ba14c94d554b58","mcp_get_code":{"code_sha256":"a2ba14c94d554b58"}},{"arxiv_id":"2503.06592","paper":"/paper/automated-proof-of-polynomial-inequalities","title":"Automated Proof of Polynomial Inequalities via Reinforcement Learning","date":"2025-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blliu6/APPIRL","path":"proof/dqn.py","file_url":"https://github.com/blliu6/APPIRL/blob/HEAD/proof/dqn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"481aca1daf0d80ec","mcp_get_code":{"code_sha256":"481aca1daf0d80ec"}},{"arxiv_id":"2310.18803","paper":"/paper/weakly-coupled-deep-q-networks","title":"Weakly Coupled Deep Q-Networks","date":"2023-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ibrahim-elshar/WCDQN_NeurIPS","path":"src/Inv_control/WCDQN.py","file_url":"https://github.com/ibrahim-elshar/WCDQN_NeurIPS/blob/HEAD/src/Inv_control/WCDQN.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"10469ffead06c867","mcp_get_code":{"code_sha256":"10469ffead06c867"}},{"arxiv_id":"2104.14138","paper":"/paper/adapting-to-reward-progressivity-via-spectral-1","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","date":"2021-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mchldann/SpectralDQN","path":"agent/dqn.py","file_url":"https://github.com/mchldann/SpectralDQN/blob/HEAD/agent/dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"code_sha256_prefix":"957ce6e2d60df983","mcp_get_code":{"code_sha256":"957ce6e2d60df983"}},{"arxiv_id":"2012.08950","paper":"/paper/deep-reinforcement-learning-of-graph-matching","title":"Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching","date":"2020-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thinklab-sjtu/rgm","path":"dqn_model_r.py","file_url":"https://github.com/thinklab-sjtu/rgm/blob/HEAD/dqn_model_r.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"29cec35c08a131ba","mcp_get_code":{"code_sha256":"29cec35c08a131ba"}},{"arxiv_id":"2002.04839","paper":"/paper/laprop-a-better-way-to-combine-momentum-with","title":"LaProp: Separating Momentum and Adaptivity in Adam","date":"2020-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Z-T-WANG/LaProp-Optimizer","path":"rainbow/model.py","file_url":"https://github.com/Z-T-WANG/LaProp-Optimizer/blob/HEAD/rainbow/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ed2dc93a9723ec69","mcp_get_code":{"code_sha256":"ed2dc93a9723ec69"}},{"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":"xgfelicia/Reinforcement-Learning","path":"Cartpole/double-dqn.py","file_url":"https://github.com/xgfelicia/Reinforcement-Learning/blob/HEAD/Cartpole/double-dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8002739ef399b9f8","mcp_get_code":{"code_sha256":"8002739ef399b9f8"}},{"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":"kmdanielduan/DQN_Family_PyTorch","path":"agent.py","file_url":"https://github.com/kmdanielduan/DQN_Family_PyTorch/blob/HEAD/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"249aaac189a4c179","mcp_get_code":{"code_sha256":"249aaac189a4c179"}},{"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":"0493df484647c5af","mcp_get_code":{"code_sha256":"0493df484647c5af"}},{"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":"yzheng51/rl-dino-run","path":"agent.py","file_url":"https://github.com/yzheng51/rl-dino-run/blob/HEAD/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4cd993bb1241d36c","mcp_get_code":{"code_sha256":"4cd993bb1241d36c"}},{"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":"OscarHuangWind/Preference-Guided-DQN-Atari","path":"DRL.py","file_url":"https://github.com/OscarHuangWind/Preference-Guided-DQN-Atari/blob/HEAD/DRL.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5964c193c9302049","mcp_get_code":{"code_sha256":"5964c193c9302049"}},{"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":"ifestus/rl","path":"dqn/dqn.py","file_url":"https://github.com/ifestus/rl/blob/HEAD/dqn/dqn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c00e8186282ff76","mcp_get_code":{"code_sha256":"2c00e8186282ff76"}},{"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":"tensorlayer/RLzoo","path":"rlzoo/algorithms/dqn/dqn.py","file_url":"https://github.com/tensorlayer/RLzoo/blob/HEAD/rlzoo/algorithms/dqn/dqn.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":"39cd1cea29282ec1","mcp_get_code":{"code_sha256":"39cd1cea29282ec1"}},{"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":"bay3s/dqn","path":"src/agents/dqn.py","file_url":"https://github.com/bay3s/dqn/blob/HEAD/src/agents/dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9c1d06fe674d019d","mcp_get_code":{"code_sha256":"9c1d06fe674d019d"}},{"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":"TheFebrin/DeepRL-Pong","path":"models/dqn_model.py","file_url":"https://github.com/TheFebrin/DeepRL-Pong/blob/HEAD/models/dqn_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a54a3b810f63e7d1","mcp_get_code":{"code_sha256":"a54a3b810f63e7d1"}},{"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":"MaximeVandegar/Papers-in-100-Lines-of-Code","path":"Playing_Atari_with_Deep_Reinforcement_Learning/dqn.py","file_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/blob/HEAD/Playing_Atari_with_Deep_Reinforcement_Learning/dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc31fb79a4c9cfad","mcp_get_code":{"code_sha256":"cc31fb79a4c9cfad"}},{"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":"daviddcho/supermario","path":"model.py","file_url":"https://github.com/daviddcho/supermario/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":"e65d2c13d9aa7641","mcp_get_code":{"code_sha256":"e65d2c13d9aa7641"}},{"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":"gordicaleksa/pytorch-learn-reinforcement-learning","path":"models/definitions/DQN.py","file_url":"https://github.com/gordicaleksa/pytorch-learn-reinforcement-learning/blob/HEAD/models/definitions/DQN.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"51cf7eff17d1081c","mcp_get_code":{"code_sha256":"51cf7eff17d1081c"}},{"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":"K-tang-mkv/baseRLAlgorithm","path":"algorithms/DQN_pytorch_offical/dqn.py","file_url":"https://github.com/K-tang-mkv/baseRLAlgorithm/blob/HEAD/algorithms/DQN_pytorch_offical/dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ac5ee56c6e889b6","mcp_get_code":{"code_sha256":"7ac5ee56c6e889b6"}},{"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":"vincentpalma/DQN-for-CaRL","path":"dqn_training.py","file_url":"https://github.com/vincentpalma/DQN-for-CaRL/blob/HEAD/dqn_training.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c7a2e9b74e4de596","mcp_get_code":{"code_sha256":"c7a2e9b74e4de596"}},{"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":"anita-hu/TF2-RL","path":"DQN/TF2_DQN_Basic.py","file_url":"https://github.com/anita-hu/TF2-RL/blob/HEAD/DQN/TF2_DQN_Basic.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7a2a672d94b88c2c","mcp_get_code":{"code_sha256":"7a2a672d94b88c2c"}},{"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":"eublefar/dqn","path":"dqn.py","file_url":"https://github.com/eublefar/dqn/blob/HEAD/dqn.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5114ef5f140eab1f","mcp_get_code":{"code_sha256":"5114ef5f140eab1f"}},{"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":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"01a1660b174e9811","mcp_get_code":{"code_sha256":"01a1660b174e9811"}}]}