{"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/noisylinear","entry":"NoisyLinear","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":9,"n_papers_ran":8,"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":9,"n_samples_ran":8,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":8,"unverified":1},"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":"2602.00051","paper":"/paper/arxiv-2602-00051","title":"Distributional Reinforcement Learning for Condition-Based Maintenance of Multi-Pump Equipment","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"tk-yasuno/dql-aged-multi-pumps-cbm","path":"train_pump_cbm_v047_enhanced.py","file_url":"https://github.com/tk-yasuno/dql-aged-multi-pumps-cbm/blob/HEAD/train_pump_cbm_v047_enhanced.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6bfa72f22914e830","mcp_get_code":{"code_sha256":"6bfa72f22914e830"}},{"arxiv_id":"2411.03820","paper":"/paper/beyond-the-rainbow-high-performance-deep","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","date":"2024-11-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rickyegl/BeyondTheRainbowICLR","path":"Agent.py","file_url":"https://github.com/rickyegl/BeyondTheRainbowICLR/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":"9e6f2536b7248907","mcp_get_code":{"code_sha256":"9e6f2536b7248907"}},{"arxiv_id":"2211.00801","paper":"/paper/multi-agent-reinforcement-learning-for-13","title":"Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement","date":"2022-11-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"011235813/marl-amr","path":"marl_amr/alg/custom_graphnet.py","file_url":"https://github.com/011235813/marl-amr/blob/HEAD/marl_amr/alg/custom_graphnet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"36056784ebb39ccd","mcp_get_code":{"code_sha256":"36056784ebb39ccd"}},{"arxiv_id":"2111.09189","paper":"/paper/tom2c-target-oriented-multi-agent-1","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","date":"2021-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"unrealtracking/tom2c","path":"model.py","file_url":"https://github.com/unrealtracking/tom2c/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"70caf124d2abab91","mcp_get_code":{"code_sha256":"70caf124d2abab91"}},{"arxiv_id":"2104.14138","paper":"/paper/adapting-to-reward-progressivity-via-spectral-1","title":"Adapting to Reward Progressivity via Spectral Reinforcement Learning","date":"2021-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mchldann/SpectralDQN","path":"agent/dqn.py","file_url":"https://github.com/mchldann/SpectralDQN/blob/HEAD/agent/dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"code_sha256_prefix":"6340add9d62a55fe","mcp_get_code":{"code_sha256":"6340add9d62a55fe"}},{"arxiv_id":"2010.03768","paper":"/paper/alfworld-aligning-text-and-embodied","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","date":"2020-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alfworld/alfworld","path":"alfworld/agents/modules/model.py","file_url":"https://github.com/alfworld/alfworld/blob/HEAD/alfworld/agents/modules/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a81a851773abf04b","mcp_get_code":{"code_sha256":"a81a851773abf04b"}},{"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":"Kaixhin/NoisyNet-A3C","path":"model.py","file_url":"https://github.com/Kaixhin/NoisyNet-A3C/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d56ce68005b7b2e2","mcp_get_code":{"code_sha256":"d56ce68005b7b2e2"}},{"arxiv_id":"1509.06461","paper":"/paper/deep-reinforcement-learning-with-double-q","title":"Deep Reinforcement Learning with Double Q-learning","date":"2015-09-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"daviddcho/supermario","path":"agent.py","file_url":"https://github.com/daviddcho/supermario/blob/HEAD/agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"00c916fc3622888b","mcp_get_code":{"code_sha256":"00c916fc3622888b"}},{"arxiv_id":"1312.5602","paper":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chandar-lab/RLHive","path":"hive/agents/qnets/atari/nature_atari_dqn.py","file_url":"https://github.com/chandar-lab/RLHive/blob/HEAD/hive/agents/qnets/atari/nature_atari_dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2d32d93aef8dd96","mcp_get_code":{"code_sha256":"e2d32d93aef8dd96"}}]}