{"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/safemean","entry":"safemean","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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2112.15400","paper":"/paper/settling-the-bias-and-variance-of-meta","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","date":"2021-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Benjamin-eecs/Theoretical-GMRL","path":"mgrl/main_meta_condition_kl.py","file_url":"https://github.com/Benjamin-eecs/Theoretical-GMRL/blob/HEAD/mgrl/main_meta_condition_kl.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7b323241cd70612","mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"arxiv_id":"1912.01588","paper":"/paper/leveraging-procedural-generation-to-benchmark","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","date":"2019-12-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ana-tudor/classyconditioning","path":"fruitbot_ppo/ppo_agent.py","file_url":"https://github.com/ana-tudor/classyconditioning/blob/HEAD/fruitbot_ppo/ppo_agent.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"a7b323241cd70612","mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"arxiv_id":"1910.09191","paper":"/paper/regularization-matters-in-policy-optimization-1","title":"Regularization Matters in Policy Optimization","date":"2019-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"a7b323241cd70612","mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"arxiv_id":"1905.02363","paper":"/paper/dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungyulhan/disc","path":"baselines/DISC/DISC.py","file_url":"https://github.com/seungyulhan/disc/blob/HEAD/baselines/DISC/DISC.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7b323241cd70612","mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"arxiv_id":"1804.06459","paper":"/paper/on-learning-intrinsic-rewards-for-policy","title":"On Learning Intrinsic Rewards for Policy Gradient Methods","date":"2018-04-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Hwhitetooth/lirpg","path":"baselines/a2c/a2c.py","file_url":"https://github.com/Hwhitetooth/lirpg/blob/HEAD/baselines/a2c/a2c.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"a7b323241cd70612","mcp_get_code":{"code_sha256":"a7b323241cd70612"}},{"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":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"a7b323241cd70612","mcp_get_code":{"code_sha256":"a7b323241cd70612"}}]}