{"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/update-mean-var-count-from-moments","entry":"update_mean_var_count_from_moments","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":14,"n_papers_ran":11,"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":7,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":15,"n_places_pointer_only":4,"by_status":{"ran_honours":3,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":3},"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":"2605.10734","paper":"/paper/arxiv-2605-10734","title":"XQCfD: Accelerating Fast Actor-Critic Algorithms with Prior Data and Prior Policies","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"danielpalenicek/xqc","path":"xqc/normalization/normalization.py","file_url":"https://github.com/danielpalenicek/xqc/blob/HEAD/xqc/normalization/normalization.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c88307cb3ede2357","mcp_get_code":{"code_sha256":"c88307cb3ede2357"}},{"arxiv_id":"2505.11289","paper":"/paper/2505-11289","title":"Meta-World+: An Improved, Standardized, RL Benchmark","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"farama-foundation/metaworld","path":"metaworld/wrappers.py","file_url":"https://github.com/farama-foundation/metaworld/blob/HEAD/metaworld/wrappers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"2311.03351","paper":"/paper/uni-o4-unifying-online-and-offline-deep","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","date":"2023-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Lei-Kun/Uni-O4","path":"ppo_finetune/normalization.py","file_url":"https://github.com/Lei-Kun/Uni-O4/blob/HEAD/ppo_finetune/normalization.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"2303.01497","paper":"/paper/teach-a-robot-to-fish-versatile-imitation","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","date":"2023-03-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siddhanthaldar/FISH","path":"FISH/utils.py","file_url":"https://github.com/siddhanthaldar/FISH/blob/HEAD/FISH/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"19a25f21c8bbd6b7","mcp_get_code":{"code_sha256":"19a25f21c8bbd6b7"}},{"arxiv_id":"2302.00965","paper":"/paper/visual-imitation-learning-with-patch-rewards","title":"Visual Imitation Learning with Patch Rewards","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sail-sg/PatchAIL","path":"PatchAIL/utils.py","file_url":"https://github.com/sail-sg/PatchAIL/blob/HEAD/PatchAIL/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"19a25f21c8bbd6b7","mcp_get_code":{"code_sha256":"19a25f21c8bbd6b7"}},{"arxiv_id":"2205.07536","paper":"/paper/reachability-constrained-reinforcement","title":"Reachability Constrained Reinforcement Learning","date":"2022-05-16","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":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"2105.14111","paper":"/paper/objective-robustness-in-deep-reinforcement","title":"Goal Misgeneralization in Deep Reinforcement Learning","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"UlisseMini/procgen-tools","path":"procgen_tools/procgen_wrappers.py","file_url":"https://github.com/UlisseMini/procgen-tools/blob/HEAD/procgen_tools/procgen_wrappers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"2105.10682","paper":"/paper/feasible-actor-critic-constrained","title":"Feasible Actor-Critic: Constrained Reinforcement Learning for Ensuring Statewise Safety","date":"2021-05-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mahaitongdae/Feasible-Actor-Critic","path":"preprocessor.py","file_url":"https://github.com/mahaitongdae/Feasible-Actor-Critic/blob/HEAD/preprocessor.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"2009.04416","paper":"/paper/phasic-policy-gradient","title":"Phasic Policy Gradient","date":"2020-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"openai/phasic-policy-gradient","path":"phasic_policy_gradient/reward_normalizer.py","file_url":"https://github.com/openai/phasic-policy-gradient/blob/HEAD/phasic_policy_gradient/reward_normalizer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d501c1a9124aff24","mcp_get_code":{"code_sha256":"d501c1a9124aff24"}},{"arxiv_id":"2006.14171","paper":"/paper/a-closer-look-at-invalid-action-masking-in","title":"A Closer Look at Invalid Action Masking in Policy Gradient Algorithms","date":"2020-06-25","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":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"2006.13916","paper":"/paper/off-dynamics-reinforcement-learning-training","title":"Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers","date":"2020-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pauldaoudi/food","path":"agents/algos_utils/darc_utils/networks_manager.py","file_url":"https://github.com/pauldaoudi/food/blob/HEAD/agents/algos_utils/darc_utils/networks_manager.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2024afc1a6905ff","mcp_get_code":{"code_sha256":"e2024afc1a6905ff"}},{"arxiv_id":"2002.11879","paper":"/paper/state-only-imitation-with-transition-dynamics-1","title":"State-only Imitation with Transition Dynamics Mismatch","date":"2020-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tgangwani/RL-Indirect-imitation","path":"i2l/networks/discriminator_model.py","file_url":"https://github.com/tgangwani/RL-Indirect-imitation/blob/HEAD/i2l/networks/discriminator_model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"cd9eda20e5749b52","mcp_get_code":{"code_sha256":"cd9eda20e5749b52"}},{"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":"joonleesky/train-procgen-pytorch","path":"common/env/procgen_wrappers.py","file_url":"https://github.com/joonleesky/train-procgen-pytorch/blob/HEAD/common/env/procgen_wrappers.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"1901.09184","paper":"/paper/action-robust-reinforcement-learning-and","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","date":"2019-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icml2019-anonymous-author/Action-Robust-Reinforcement-Learning","path":"utils.py","file_url":"https://github.com/icml2019-anonymous-author/Action-Robust-Reinforcement-Learning/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3ebb420a5d10cc64","mcp_get_code":{"code_sha256":"3ebb420a5d10cc64"}},{"arxiv_id":"1901.09184","paper":"/paper/action-robust-reinforcement-learning-and","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","date":"2019-01-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"icml2019-anonymous-author/Action-Robust-Reinforcement-Learning","path":"normalized_actions.py","file_url":"https://github.com/icml2019-anonymous-author/Action-Robust-Reinforcement-Learning/blob/HEAD/normalized_actions.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bc3dde5f5f1ac8e2","mcp_get_code":{"code_sha256":"bc3dde5f5f1ac8e2"}}]}