{"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/ounoise","entry":"OUNoise","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":6,"n_papers_ran":6,"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":18,"n_samples_ran":18,"n_samples_fingerprinted":0,"n_places":18,"n_places_pointer_only":14,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":18,"unverified":0},"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":"2604.19146","paper":"/paper/arxiv-2604-19146","title":"RL-ABC: Reinforcement Learning for Accelerator Beamline Control","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Anwar9Ibrahim/RL-ABC","path":"rl_framework/Agents/DDPG.py","file_url":"https://github.com/Anwar9Ibrahim/RL-ABC/blob/HEAD/rl_framework/Agents/DDPG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1ab3164a1f62a5a","mcp_get_code":{"code_sha256":"a1ab3164a1f62a5a"}},{"arxiv_id":"2305.12239","paper":"/paper/off-policy-average-reward-actor-critic-with","title":"Off-Policy Average Reward Actor-Critic with Deterministic Policy Search","date":"2023-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yhisaki/average-reward-drl","path":"average_reward_drl/algorithms/aro_ddpg.py","file_url":"https://github.com/yhisaki/average-reward-drl/blob/HEAD/average_reward_drl/algorithms/aro_ddpg.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e3101a1ad8f1b30","mcp_get_code":{"code_sha256":"1e3101a1ad8f1b30"}},{"arxiv_id":"2203.08553","paper":"/paper/pmic-improving-multi-agent-reinforcement-1","title":"PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration","date":"2022-03-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yeshenpy/pmic","path":"algorithms/mpe_new_maxminMADDPG.py","file_url":"https://github.com/yeshenpy/pmic/blob/HEAD/algorithms/mpe_new_maxminMADDPG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5a6b141fd404c7c4","mcp_get_code":{"code_sha256":"5a6b141fd404c7c4"}},{"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":"MrDaubinet/collaboration-and-competition","path":"maddpg.py","file_url":"https://github.com/MrDaubinet/collaboration-and-competition/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":"db3bd13d21d6150c","mcp_get_code":{"code_sha256":"db3bd13d21d6150c"}},{"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":"biemann/Collaboration-and-Competition","path":"maddpg.py","file_url":"https://github.com/biemann/Collaboration-and-Competition/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":"555ae48ebffc59d4","mcp_get_code":{"code_sha256":"555ae48ebffc59d4"}},{"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":"krasing/DRLearningCollaboration","path":"failed_collaborative/ddpg_agent_multi_2.py","file_url":"https://github.com/krasing/DRLearningCollaboration/blob/HEAD/failed_collaborative/ddpg_agent_multi_2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a169b2555a871836","mcp_get_code":{"code_sha256":"a169b2555a871836"}},{"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":"Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment","path":"ddpg_agent.py","file_url":"https://github.com/Remtasya/DDPG-Actor-Critic-Reinforcement-Learning-Reacher-Environment/blob/HEAD/ddpg_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1f98ee39e6a11d66","mcp_get_code":{"code_sha256":"1f98ee39e6a11d66"}},{"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":"dpoulopoulos/drl_collaborate_compete","path":"ddpg_agent.py","file_url":"https://github.com/dpoulopoulos/drl_collaborate_compete/blob/HEAD/ddpg_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e47034c4a39da307","mcp_get_code":{"code_sha256":"e47034c4a39da307"}},{"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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"85896c6b57d5891f","mcp_get_code":{"code_sha256":"85896c6b57d5891f"}},{"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":"iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient","path":"ddpg_agent.py","file_url":"https://github.com/iDataist/Continuous-Control-with-Deep-Deterministic-Policy-Gradient/blob/HEAD/ddpg_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f0163af304a40792","mcp_get_code":{"code_sha256":"f0163af304a40792"}},{"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":"dan-lennox/ml-udacity-quadcopter-rl","path":"agents/agent.py","file_url":"https://github.com/dan-lennox/ml-udacity-quadcopter-rl/blob/HEAD/agents/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"046c7d82e0f35a06","mcp_get_code":{"code_sha256":"046c7d82e0f35a06"}},{"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":"IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env","path":"ddpg_agent.py","file_url":"https://github.com/IvanVigor/Deep-Deterministic-Policy-Gradient-Unity-Env/blob/HEAD/ddpg_agent.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":"d7af24edd798e11c","mcp_get_code":{"code_sha256":"d7af24edd798e11c"}},{"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":"EyaRhouma/collaboration-competition-MADDPG","path":"MADDPG_agent.py","file_url":"https://github.com/EyaRhouma/collaboration-competition-MADDPG/blob/HEAD/MADDPG_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0562ed655f21cba8","mcp_get_code":{"code_sha256":"0562ed655f21cba8"}},{"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":"ZainRaza14/deepRL","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/ZainRaza14/deepRL/blob/HEAD/DDPG/ddpg_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"21303179927140a0","mcp_get_code":{"code_sha256":"21303179927140a0"}},{"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":"madhur-tandon/RL-Project","path":"agent.py","file_url":"https://github.com/madhur-tandon/RL-Project/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":"7e2a8290108cb3ea","mcp_get_code":{"code_sha256":"7e2a8290108cb3ea"}},{"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":"biemann/Continuous-Control","path":"ddpg_agent.py","file_url":"https://github.com/biemann/Continuous-Control/blob/HEAD/ddpg_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06e140e447cd7fb3","mcp_get_code":{"code_sha256":"06e140e447cd7fb3"}},{"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":"claudeHifly/BipedalWalker-v3","path":"DDPG/ddpg_agent.py","file_url":"https://github.com/claudeHifly/BipedalWalker-v3/blob/HEAD/DDPG/ddpg_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"affd388fecde62eb","mcp_get_code":{"code_sha256":"affd388fecde62eb"}},{"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":"WittmannF/quadcopter-best-practices","path":"agent.py","file_url":"https://github.com/WittmannF/quadcopter-best-practices/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":"6d50e581fbec00bb","mcp_get_code":{"code_sha256":"6d50e581fbec00bb"}}]}