{"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/format-samples-for-training","entry":"format_samples_for_training","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":7,"n_papers_ran":7,"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":0,"n_places":7,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"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":"2307.11352","paper":"/paper/model-based-offline-reinforcement-learning-2","title":"Model-based Offline Reinforcement Learning with Count-based Conservatism","date":"2023-07-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"oh-lab/count-morl","path":"mopo.py","file_url":"https://github.com/oh-lab/count-morl/blob/HEAD/mopo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bb5583dba32f555","mcp_get_code":{"code_sha256":"1bb5583dba32f555"}},{"arxiv_id":"2212.00124","paper":"/paper/one-risk-to-rule-them-all-a-risk-sensitive-1","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"marc-rigter/1R2R","path":"_1R2R/models/constructor.py","file_url":"https://github.com/marc-rigter/1R2R/blob/HEAD/_1R2R/models/constructor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bb5583dba32f555","mcp_get_code":{"code_sha256":"1bb5583dba32f555"}},{"arxiv_id":"2105.09452","paper":"/paper/minimum-delay-adaptation-in-non-stationary","title":"Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection","date":"2021-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LucasAlegre/mbcd","path":"mbcd/models/constructor.py","file_url":"https://github.com/LucasAlegre/mbcd/blob/HEAD/mbcd/models/constructor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bb5583dba32f555","mcp_get_code":{"code_sha256":"1bb5583dba32f555"}},{"arxiv_id":"2105.06350","paper":"/paper/mapgo-model-assisted-policy-optimization-for","title":"MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks","date":"2021-05-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apexrl/MapGo","path":"dynamic/mbpo_model/constructor.py","file_url":"https://github.com/apexrl/MapGo/blob/HEAD/dynamic/mbpo_model/constructor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bb5583dba32f555","mcp_get_code":{"code_sha256":"1bb5583dba32f555"}},{"arxiv_id":"2103.13842","paper":"/paper/model-predictive-actor-critic-accelerating","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","date":"2021-03-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dnandha/mopac","path":"mopac/models/constructor.py","file_url":"https://github.com/dnandha/mopac/blob/HEAD/mopac/models/constructor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bb5583dba32f555","mcp_get_code":{"code_sha256":"1bb5583dba32f555"}},{"arxiv_id":"2010.09546","paper":"/paper/model-based-policy-optimization-with","title":"Model-based Policy Optimization with Unsupervised Model Adaptation","date":"2020-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"RockySJ/ampo","path":"models/constructor.py","file_url":"https://github.com/RockySJ/ampo/blob/HEAD/models/constructor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bb5583dba32f555","mcp_get_code":{"code_sha256":"1bb5583dba32f555"}},{"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":"JannerM/mbpo","path":"mbpo/models/constructor.py","file_url":"https://github.com/JannerM/mbpo/blob/HEAD/mbpo/models/constructor.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1bb5583dba32f555","mcp_get_code":{"code_sha256":"1bb5583dba32f555"}}]}