{"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/runningmeanstd","entry":"RunningMeanStd","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":13,"n_papers_ran":13,"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":2,"n_places":13,"n_places_pointer_only":3,"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":"2601.11441","paper":"/paper/arxiv-2601-11441","title":"Hierarchical Orthogonal Residual Spread for Precise Massive Editing in Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"XiaojieGu/HORSE","path":"editor/horse.py","file_url":"https://github.com/XiaojieGu/HORSE/blob/HEAD/editor/horse.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0b6b62c3b65c34da","mcp_get_code":{"code_sha256":"0b6b62c3b65c34da"}},{"arxiv_id":"2406.19972","paper":"/paper/humanvla-towards-vision-language-directed","title":"HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid","date":null,"month_inferred_from_arxiv_id":"2024-06","title_source":"archive","repo":"AllenXuuu/HumanVLA","path":"models/dagger/vla_network.py","file_url":"https://github.com/AllenXuuu/HumanVLA/blob/HEAD/models/dagger/vla_network.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"94e925f5c51f7d0c","mcp_get_code":{"code_sha256":"94e925f5c51f7d0c"}},{"arxiv_id":"2404.10740","paper":"/paper/n-agent-ad-hoc-teamwork","title":"N-Agent Ad Hoc Teamwork","date":"2024-04-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"carolinewang01/naht","path":"src/learners/poam_learner.py","file_url":"https://github.com/carolinewang01/naht/blob/HEAD/src/learners/poam_learner.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cdfc3ae6a09e2c06","mcp_get_code":{"code_sha256":"cdfc3ae6a09e2c06"}},{"arxiv_id":"2402.17257","paper":"/paper/rime-robust-preference-based-reinforcement","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cjreinforce/rime_icml2024","path":"reward_model_RIME.py","file_url":"https://github.com/cjreinforce/rime_icml2024/blob/HEAD/reward_model_RIME.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"60d6d08eefa30cf7","mcp_get_code":{"code_sha256":"60d6d08eefa30cf7"}},{"arxiv_id":"2310.17537","paper":"/paper/neuro-inspired-fragmentation-and-recall-to","title":"Neuro-Inspired Fragmentation and Recall to Overcome Catastrophic Forgetting in Curiosity","date":"2023-10-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fietelab/farcuriosity","path":"rlpyt/models/curiosity/fragmentation_wrapper.py","file_url":"https://github.com/fietelab/farcuriosity/blob/HEAD/rlpyt/models/curiosity/fragmentation_wrapper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c9b232c9c0357ca3","mcp_get_code":{"code_sha256":"c9b232c9c0357ca3"}},{"arxiv_id":"2307.08875","paper":"/paper/natural-actor-critic-for-robust-reinforcement","title":"Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation","date":"2023-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tliu1997/rnac","path":"train_rnac.py","file_url":"https://github.com/tliu1997/rnac/blob/HEAD/train_rnac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"8b5734917fdb6af3","mcp_get_code":{"code_sha256":"8b5734917fdb6af3"}},{"arxiv_id":"2206.08853","paper":"/paper/minedojo-building-open-ended-embodied-agents","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","date":"2022-06-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pku-rl/copl","path":"src/core/ppo.py","file_url":"https://github.com/pku-rl/copl/blob/HEAD/src/core/ppo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"327090e4d81e9be1","mcp_get_code":{"code_sha256":"327090e4d81e9be1"}},{"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":"mahaitongdae/Reachability_Constrained_RL","path":"learners/sac.py","file_url":"https://github.com/mahaitongdae/Reachability_Constrained_RL/blob/HEAD/learners/sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e4fcdf4a34ebca39","mcp_get_code":{"code_sha256":"e4fcdf4a34ebca39"}},{"arxiv_id":"2110.10083","paper":"/paper/contrastive-active-inference","title":"Contrastive Active Inference","date":"2021-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mazpie/contrastive-aif","path":"agents.py","file_url":"https://github.com/mazpie/contrastive-aif/blob/HEAD/agents.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"09d1b0e1811952ff","mcp_get_code":{"code_sha256":"09d1b0e1811952ff"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"54a2a67d3023c95b","mcp_get_code":{"code_sha256":"54a2a67d3023c95b"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"717e531be45c1f47","mcp_get_code":{"code_sha256":"717e531be45c1f47"}},{"arxiv_id":"2002.06038","paper":"/paper/never-give-up-learning-directed-exploration-1","title":"Never Give Up: Learning Directed Exploration Strategies","date":"2020-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"YHL04/agent57","path":"curiosity/episodicnovelty.py","file_url":"https://github.com/YHL04/agent57/blob/HEAD/curiosity/episodicnovelty.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a78127c40ebe35aa","mcp_get_code":{"code_sha256":"a78127c40ebe35aa"}},{"arxiv_id":"1511.05952","paper":"/paper/prioritized-experience-replay","title":"Prioritized Experience Replay","date":"2015-11-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hill-a/stable-baselines","path":"stable_baselines/common/buffers.py","file_url":"https://github.com/hill-a/stable-baselines/blob/HEAD/stable_baselines/common/buffers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7d869ac145d41f2","mcp_get_code":{"code_sha256":"a7d869ac145d41f2"}}]}