{"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/qnetwork","entry":"QNetwork","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":11,"n_papers_ran":10,"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":16,"n_samples_ran":15,"n_samples_fingerprinted":1,"n_places":16,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":15,"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":"2606.21173","paper":"/paper/arxiv-2606-21173","title":"Inverting the Bellman Equation: From Q-Values to World Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"aletcher/inverting-bellman","path":"training/wm.py","file_url":"https://github.com/aletcher/inverting-bellman/blob/HEAD/training/wm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"549021cbd6349871","mcp_get_code":{"code_sha256":"549021cbd6349871"}},{"arxiv_id":"2606.09869","paper":"/paper/arxiv-2606-09869","title":"QSplitFL: Capability Aware Deep Q-Learning for Optimal Split Point Selection in Split Federated Learning Nazmus Shakib Shadin 1[0000-0002-0999-924X] , Xinyue Zhang 1[0000-0002-4243-083X] , Jingyi Wang 2[0000-0002-4988-5626] , and Miao Pan 3[0000-0003-2138-4413]","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"AIPO-Lab/QSplitFL","path":"Capability_Aware_DQN_Implementation/dqn_split_agent.py","file_url":"https://github.com/AIPO-Lab/QSplitFL/blob/HEAD/Capability_Aware_DQN_Implementation/dqn_split_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3e6be4fc6204efdf","mcp_get_code":{"code_sha256":"3e6be4fc6204efdf"}},{"arxiv_id":"2501.02087","paper":"/paper/beyond-cvar-leveraging-static-spectral-risk","title":"Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning","date":"2025-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mehrdadmoghimi/qrsrm","path":"qrsrm.py","file_url":"https://github.com/mehrdadmoghimi/qrsrm/blob/HEAD/qrsrm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f373e451c4a47bfb","mcp_get_code":{"code_sha256":"f373e451c4a47bfb"}},{"arxiv_id":"2409.04792","paper":"/paper/improving-deep-reinforcement-learning-by","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","date":"2024-09-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bluecontra/CHAIN","path":"minatar/agents/double_dqn_chain.py","file_url":"https://github.com/bluecontra/CHAIN/blob/HEAD/minatar/agents/double_dqn_chain.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2bc9d20a97ad4b7c","mcp_get_code":{"code_sha256":"2bc9d20a97ad4b7c"}},{"arxiv_id":"2302.12902","paper":"/paper/the-dormant-neuron-phenomenon-in-deep","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","date":"2023-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"timoklein/redo","path":"src/redo.py","file_url":"https://github.com/timoklein/redo/blob/HEAD/src/redo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"09bc70233cc3c184","mcp_get_code":{"code_sha256":"09bc70233cc3c184"}},{"arxiv_id":"2010.08830","paper":"/paper/mesa-boost-ensemble-imbalanced-learning-with","title":"MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler","date":"2020-10-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NeurIPS2020AnonymousSubmission/mesa","path":"mesa.py","file_url":"https://github.com/NeurIPS2020AnonymousSubmission/mesa/blob/HEAD/mesa.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ff10fc4473be092a","mcp_get_code":{"code_sha256":"ff10fc4473be092a"}},{"arxiv_id":"2007.14430","paper":"/paper/munchausen-reinforcement-learning","title":"Munchausen Reinforcement Learning","date":"2020-07-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lingweizhu/Pytorch-MunchausenActorCritic","path":"Munchausen_actorcritic_discrete/agent/munchausen_ac.py","file_url":"https://github.com/lingweizhu/Pytorch-MunchausenActorCritic/blob/HEAD/Munchausen_actorcritic_discrete/agent/munchausen_ac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c0deed6c236f0456","mcp_get_code":{"code_sha256":"c0deed6c236f0456"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Rafael1s/Deep-Reinforcement-Learning-Udacity","path":"Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","file_url":"https://github.com/Rafael1s/Deep-Reinforcement-Learning-Udacity/blob/HEAD/Ant-PyBulletEnv-Soft-Actor-Critic/sac_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f37748964b0cd7da","mcp_get_code":{"code_sha256":"f37748964b0cd7da"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thomashirtz/soft-actor-critic","path":"soft_actor_critic/agent.py","file_url":"https://github.com/thomashirtz/soft-actor-critic/blob/HEAD/soft_actor_critic/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b7030d8d56cd639a","mcp_get_code":{"code_sha256":"b7030d8d56cd639a"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"roythuly/obac","path":"model/algo.py","file_url":"https://github.com/roythuly/obac/blob/HEAD/model/algo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d80189fd77d3aa6","mcp_get_code":{"code_sha256":"0d80189fd77d3aa6"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"MarsEleven/car_racer_RL","path":"sac/sac.py","file_url":"https://github.com/MarsEleven/car_racer_RL/blob/HEAD/sac/sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e3aca820c0049604","mcp_get_code":{"code_sha256":"e3aca820c0049604"}},{"arxiv_id":"1801.01290","paper":"/paper/soft-actor-critic-off-policy-maximum-entropy","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","date":"2018-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ajaysub110/rl-pytorch","path":"sac/models/soft_actor_critic.py","file_url":"https://github.com/ajaysub110/rl-pytorch/blob/HEAD/sac/models/soft_actor_critic.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e182a5c8f1d1e16f","mcp_get_code":{"code_sha256":"e182a5c8f1d1e16f"}},{"arxiv_id":"1702.08165","paper":"/paper/reinforcement-learning-with-deep-energy-based","title":"Reinforcement Learning with Deep Energy-Based Policies","date":"2017-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shakedzy/warehouse","path":"gin/dqn.py","file_url":"https://github.com/shakedzy/warehouse/blob/HEAD/gin/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":"27dea380484a6401","mcp_get_code":{"code_sha256":"27dea380484a6401"}},{"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":"MEOWMEOW114/nd893-p1-navigation-banana","path":"dqn/double_dqn_agent.py","file_url":"https://github.com/MEOWMEOW114/nd893-p1-navigation-banana/blob/HEAD/dqn/double_dqn_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f9462232ec862c47","mcp_get_code":{"code_sha256":"f9462232ec862c47"}},{"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":"Adrelf/DRL-navigation","path":"brain/dqn_agent.py","file_url":"https://github.com/Adrelf/DRL-navigation/blob/HEAD/brain/dqn_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"01d2de07d88f7c3a","mcp_get_code":{"code_sha256":"01d2de07d88f7c3a"}},{"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":"Linging/Traffic-Signal-Control","path":"Agent/networks.py","file_url":"https://github.com/Linging/Traffic-Signal-Control/blob/HEAD/Agent/networks.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"391471b2e6f9888c","mcp_get_code":{"code_sha256":"391471b2e6f9888c"}}]}