{"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/actorcritic","entry":"ActorCritic","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":10,"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":19,"n_samples_ran":13,"n_samples_fingerprinted":5,"n_places":19,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":13,"unverified":6},"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":"2603.24139","paper":"/paper/arxiv-2603-24139","title":"Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"wannac1/TSRL","path":"training/agents/tutor_grpo.py","file_url":"https://github.com/wannac1/TSRL/blob/HEAD/training/agents/tutor_grpo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e54f5d97d7a522af","mcp_get_code":{"code_sha256":"e54f5d97d7a522af"}},{"arxiv_id":"2603.03054","paper":"/paper/arxiv-2603-03054","title":"PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"sudip-bhujel/privmedchat","path":"src/ppo/model.py","file_url":"https://github.com/sudip-bhujel/privmedchat/blob/HEAD/src/ppo/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9016025ea65d495c","mcp_get_code":{"code_sha256":"9016025ea65d495c"}},{"arxiv_id":"2209.12016","paper":"/paper/unsupervised-model-based-pre-training-for","title":"Mastering the Unsupervised Reinforcement Learning Benchmark from Pixels","date":"2022-09-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mazpie/mastering-urlb","path":"agent/dreamer.py","file_url":"https://github.com/mazpie/mastering-urlb/blob/HEAD/agent/dreamer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d0b227b9789fce4a","mcp_get_code":{"code_sha256":"d0b227b9789fce4a"}},{"arxiv_id":"2105.03245","paper":"/paper/adaptive-focus-for-efficient-video","title":"Adaptive Focus for Efficient Video Recognition","date":"2021-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blackfeather-wang/AdaFocus","path":"Experiments on ActivityNet, FCVID and Mini-Kinetics/models/gfv_net.py","file_url":"https://github.com/blackfeather-wang/AdaFocus/blob/HEAD/Experiments%20on%20ActivityNet%2C%20FCVID%20and%20Mini-Kinetics/models/gfv_net.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aaf4fc54301dc25b","mcp_get_code":{"code_sha256":"aaf4fc54301dc25b"}},{"arxiv_id":"2011.01928","paper":"/paper/generalization-to-new-actions-in-1","title":"Generalization to New Actions in Reinforcement Learning","date":"2020-11-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"clvrai/new-actions-rl","path":"method/models/main_method.py","file_url":"https://github.com/clvrai/new-actions-rl/blob/HEAD/method/models/main_method.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7da11c67fbcd655c","mcp_get_code":{"code_sha256":"7da11c67fbcd655c"}},{"arxiv_id":"2010.05300","paper":"/paper/glance-and-focus-a-dynamic-approach-to","title":"Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification","date":"2020-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"blackfeather-wang/GFNet-Pytorch","path":"network.py","file_url":"https://github.com/blackfeather-wang/GFNet-Pytorch/blob/HEAD/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ff16fd088aa240e7","mcp_get_code":{"code_sha256":"ff16fd088aa240e7"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bonniesjli/PPO-Reacher_UnityML","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO-Reacher_UnityML/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":"f7a59411ac390f78","mcp_get_code":{"code_sha256":"f7a59411ac390f78"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bonniesjli/PPO_Reacher","path":"agent.py","file_url":"https://github.com/bonniesjli/PPO_Reacher/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":"607bb439a428fd2a","mcp_get_code":{"code_sha256":"607bb439a428fd2a"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nikhilbarhate99/PPO-PyTorch","path":"PPO.py","file_url":"https://github.com/nikhilbarhate99/PPO-PyTorch/blob/HEAD/PPO.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bab8cee03856463f","mcp_get_code":{"code_sha256":"bab8cee03856463f"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bay3s/ppo-rl","path":"src/ppo/ppo.py","file_url":"https://github.com/bay3s/ppo-rl/blob/HEAD/src/ppo/ppo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ff581679958bf77","mcp_get_code":{"code_sha256":"6ff581679958bf77"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuyuezhang/pyrl","path":"ppo/agent.py","file_url":"https://github.com/liuyuezhang/pyrl/blob/HEAD/ppo/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2f383d9f3f2f7b4f","mcp_get_code":{"code_sha256":"2f383d9f3f2f7b4f"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tommyvsfu1/RL-NTU","path":"RL_mlds_hw4/hw4/agent_dir/agent_pg.py","file_url":"https://github.com/tommyvsfu1/RL-NTU/blob/HEAD/RL_mlds_hw4/hw4/agent_dir/agent_pg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d068adb7cb463c20","mcp_get_code":{"code_sha256":"d068adb7cb463c20"}},{"arxiv_id":"1606.03476","paper":"/paper/generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emunaran/stochastic-human-driving-policies-drl","path":"model/algorithm/gail.py","file_url":"https://github.com/emunaran/stochastic-human-driving-policies-drl/blob/HEAD/model/algorithm/gail.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cb3f4da86ee1b680","mcp_get_code":{"code_sha256":"cb3f4da86ee1b680"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uvipen/Super-mario-bros-A3C-pytorch","path":"src/model.py","file_url":"https://github.com/uvipen/Super-mario-bros-A3C-pytorch/blob/HEAD/src/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3deab9eb1f3ddf5a","mcp_get_code":{"code_sha256":"3deab9eb1f3ddf5a"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kaixhin/ACER","path":"model.py","file_url":"https://github.com/Kaixhin/ACER/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1980413ab36cb308","mcp_get_code":{"code_sha256":"1980413ab36cb308"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sharan-dce/A3C","path":"network.py","file_url":"https://github.com/sharan-dce/A3C/blob/HEAD/network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"fc9bb6ed16967be3","mcp_get_code":{"code_sha256":"fc9bb6ed16967be3"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Kaixhin/NoisyNet-A3C","path":"model.py","file_url":"https://github.com/Kaixhin/NoisyNet-A3C/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ce452dd0eac4e57","mcp_get_code":{"code_sha256":"3ce452dd0eac4e57"}},{"arxiv_id":"1602.01783","paper":"/paper/asynchronous-methods-for-deep-reinforcement","title":"Asynchronous Methods for Deep Reinforcement Learning","date":"2016-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sainijagjit/A3C-Pytorch","path":"model.py","file_url":"https://github.com/sainijagjit/A3C-Pytorch/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":"6dc67ce074d20f64","mcp_get_code":{"code_sha256":"6dc67ce074d20f64"}},{"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":"dchetelat/acer","path":"brain.py","file_url":"https://github.com/dchetelat/acer/blob/HEAD/brain.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"26052e22d5d45a91","mcp_get_code":{"code_sha256":"26052e22d5d45a91"}}]}