{"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/gaussianpolicy","entry":"GaussianPolicy","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":7,"n_papers_ran":7,"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":13,"n_samples_ran":13,"n_samples_fingerprinted":10,"n_places":13,"n_places_pointer_only":7,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":13,"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":"2510.22027","paper":"/paper/arxiv-2510-22027","title":"Online Optimization for Offline Safe Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"yassineCh/O3SRL","path":"o3srl.py","file_url":"https://github.com/yassineCh/O3SRL/blob/HEAD/o3srl.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c1539b456860f5e0","mcp_get_code":{"code_sha256":"c1539b456860f5e0"}},{"arxiv_id":"2303.07337","paper":"/paper/poseexaminer-automated-testing-of-out-of","title":"PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation","date":"2023-03-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qihao067/PoseExaminer","path":"utils_PoseExaminer/models/policy_2step.py","file_url":"https://github.com/qihao067/PoseExaminer/blob/HEAD/utils_PoseExaminer/models/policy_2step.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e2d2696014f36496","mcp_get_code":{"code_sha256":"e2d2696014f36496"}},{"arxiv_id":"2201.11927","paper":"/paper/constrained-variational-policy-optimization","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning","date":"2022-01-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zifanwu/cal","path":"agent/cal.py","file_url":"https://github.com/zifanwu/cal/blob/HEAD/agent/cal.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a2295f0701fc2bfc","mcp_get_code":{"code_sha256":"a2295f0701fc2bfc"}},{"arxiv_id":"2107.06106","paper":"/paper/conservative-offline-distributional","title":"Conservative Offline Distributional Reinforcement Learning","date":"2021-07-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"JasonMa2016/CODAC","path":"distributional/codac.py","file_url":"https://github.com/JasonMa2016/CODAC/blob/HEAD/distributional/codac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"15db1b8d1bff5a1e","mcp_get_code":{"code_sha256":"15db1b8d1bff5a1e"}},{"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":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3393f1e0da810f3f","mcp_get_code":{"code_sha256":"3393f1e0da810f3f"}},{"arxiv_id":"2007.01932","paper":"/paper/meta-sac-auto-tune-the-entropy-temperature-of","title":"Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient","date":"2020-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"twni2016/Meta-SAC","path":"meta_sac/sacmeta.py","file_url":"https://github.com/twni2016/Meta-SAC/blob/HEAD/meta_sac/sacmeta.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dbd5981dc0704e2e","mcp_get_code":{"code_sha256":"dbd5981dc0704e2e"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bf0d89394b22e1b6","mcp_get_code":{"code_sha256":"bf0d89394b22e1b6"}},{"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":"baturaysaglam/la3p","path":"Code/SAC/SAC.py","file_url":"https://github.com/baturaysaglam/la3p/blob/HEAD/Code/SAC/SAC.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"152bc1e449547d23","mcp_get_code":{"code_sha256":"152bc1e449547d23"}},{"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":"ku2482/discor.pytorch","path":"discor/algorithm/sac.py","file_url":"https://github.com/ku2482/discor.pytorch/blob/HEAD/discor/algorithm/sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8761dc745b44dc04","mcp_get_code":{"code_sha256":"8761dc745b44dc04"}},{"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":"h-aboutalebi/SparceReward","path":"engine/algorithms/SAC/sac.py","file_url":"https://github.com/h-aboutalebi/SparceReward/blob/HEAD/engine/algorithms/SAC/sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8ee15fddb3528e86","mcp_get_code":{"code_sha256":"8ee15fddb3528e86"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"da8ebd6e9ea11fca","mcp_get_code":{"code_sha256":"da8ebd6e9ea11fca"}},{"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":"sunfex/weighted-sac","path":"sac.py","file_url":"https://github.com/sunfex/weighted-sac/blob/HEAD/sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5722a85a4a153169","mcp_get_code":{"code_sha256":"5722a85a4a153169"}},{"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":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"57c7562fda9bbab3","mcp_get_code":{"code_sha256":"57c7562fda9bbab3"}}]}