{"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/calculate-huber-loss","entry":"calculate_huber_loss","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":5,"n_papers_ran":4,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":3,"ran_fixture":0,"ran":0,"unverified":2},"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":"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_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7c1d5bc9f897b0cf","mcp_get_code":{"code_sha256":"7c1d5bc9f897b0cf"}},{"arxiv_id":"2103.16596","paper":"/paper/benchmarks-for-deep-off-policy-evaluation-1","title":"Benchmarks for Deep Off-Policy Evaluation","date":"2021-03-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tedmoskovitz/TOP","path":"dmc/top_curl_sac.py","file_url":"https://github.com/tedmoskovitz/TOP/blob/HEAD/dmc/top_curl_sac.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5bb744e06e0b22f8","mcp_get_code":{"code_sha256":"5bb744e06e0b22f8"}},{"arxiv_id":"1911.02140","paper":"/paper/fully-parameterized-quantile-function-for","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BY571/FQF-and-Extensions","path":"agent.py","file_url":"https://github.com/BY571/FQF-and-Extensions/blob/HEAD/agent.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9d455622c2dcd61","mcp_get_code":{"code_sha256":"d9d455622c2dcd61"}},{"arxiv_id":"1911.02140","paper":"/paper/fully-parameterized-quantile-function-for","title":"Fully Parameterized Quantile Function for Distributional Reinforcement Learning","date":"2019-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ku2482/fqf-iqn-qrdqn.pytorch","path":"fqf_iqn_qrdqn/utils.py","file_url":"https://github.com/ku2482/fqf-iqn-qrdqn.pytorch/blob/HEAD/fqf_iqn_qrdqn/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8467036da5b81c2f","mcp_get_code":{"code_sha256":"8467036da5b81c2f"}},{"arxiv_id":"1806.06923","paper":"/paper/implicit-quantile-networks-for-distributional","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","date":"2018-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BY571/IQN","path":"agent.py","file_url":"https://github.com/BY571/IQN/blob/HEAD/agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8563b54f28d9f9c6","mcp_get_code":{"code_sha256":"8563b54f28d9f9c6"}},{"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":"BY571/Soft-Actor-Critic-and-Extensions","path":"files/Agent.py","file_url":"https://github.com/BY571/Soft-Actor-Critic-and-Extensions/blob/HEAD/files/Agent.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d9d455622c2dcd61","mcp_get_code":{"code_sha256":"d9d455622c2dcd61"}}]}