{"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/criticnetwork","entry":"CriticNetwork","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":11,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":11,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":5},"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":"2603.24366","paper":"/paper/arxiv-2603-24366","title":"CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"marmotlab/CoordLight","path":"Models/CoordLightModel.py","file_url":"https://github.com/marmotlab/CoordLight/blob/HEAD/Models/CoordLightModel.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bda7507c3cc10545","mcp_get_code":{"code_sha256":"bda7507c3cc10545"}},{"arxiv_id":"2506.08417","paper":"/paper/offline-rl-with-smooth-ood-generalization-in","title":"Offline RL with Smooth OOD Generalization in Convex Hull and its Neighborhood","date":"2025-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yqpqry/sqog","path":"SQOG.py","file_url":"https://github.com/yqpqry/sqog/blob/HEAD/SQOG.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0c9976aa09f749fe","mcp_get_code":{"code_sha256":"0c9976aa09f749fe"}},{"arxiv_id":"2211.03413","paper":"/paper/max-min-off-policy-actor-critic-method","title":"Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification","date":"2022-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"akimotolab/m2td3","path":"M2TD3/m2td3.py","file_url":"https://github.com/akimotolab/m2td3/blob/HEAD/M2TD3/m2td3.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a72ab09853236a35","mcp_get_code":{"code_sha256":"a72ab09853236a35"}},{"arxiv_id":"1706.02275","paper":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"baradist/multiagent-particle-envs","path":"multiagent/ddpg/ddpg_agent.py","file_url":"https://github.com/baradist/multiagent-particle-envs/blob/HEAD/multiagent/ddpg/ddpg_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"619856d2049bc612","mcp_get_code":{"code_sha256":"619856d2049bc612"}},{"arxiv_id":"1706.02275","paper":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients","path":"maddpg.py","file_url":"https://github.com/philtabor/Multi-Agent-Deep-Deterministic-Policy-Gradients/blob/HEAD/maddpg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1a6507f0b27d66e3","mcp_get_code":{"code_sha256":"1a6507f0b27d66e3"}},{"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":"sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3","path":"maddpgAgent.py","file_url":"https://github.com/sliao-mi-luku/DeepRL-multiple-agents-tennis-udacity-drlnd-p3/blob/HEAD/maddpgAgent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b796e48c52beebc5","mcp_get_code":{"code_sha256":"b796e48c52beebc5"}},{"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":"T3chy/DDPG","path":"ddpg_torch.py","file_url":"https://github.com/T3chy/DDPG/blob/HEAD/ddpg_torch.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"c64a46f5ad45b01a","mcp_get_code":{"code_sha256":"c64a46f5ad45b01a"}},{"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":"KelvinYang0320/deepbots-panda","path":"Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","file_url":"https://github.com/KelvinYang0320/deepbots-panda/blob/HEAD/Panda_RL/controllers/robot_supervisor_manager/agent/ddpg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6429748a5267bb8a","mcp_get_code":{"code_sha256":"6429748a5267bb8a"}},{"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":"YoUNG824/DDPG","path":"ddpg.py","file_url":"https://github.com/YoUNG824/DDPG/blob/HEAD/ddpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ebdd58004bdf82fd","mcp_get_code":{"code_sha256":"ebdd58004bdf82fd"}},{"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":"bmeyers/VirtualMicrogridSegmentation","path":"virtual_microgrids/algorithms/ddpg.py","file_url":"https://github.com/bmeyers/VirtualMicrogridSegmentation/blob/HEAD/virtual_microgrids/algorithms/ddpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"4644458fd0a4374e","mcp_get_code":{"code_sha256":"4644458fd0a4374e"}},{"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":"samuelmat19/DDPG-tf2","path":"src/model.py","file_url":"https://github.com/samuelmat19/DDPG-tf2/blob/HEAD/src/model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6bb81ff3c30fb32a","mcp_get_code":{"code_sha256":"6bb81ff3c30fb32a"}}]}