{"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/create-env","entry":"create_env","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":6,"n_papers_ran":1,"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":6,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":1,"ran":0,"unverified":5},"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":"2310.04590","paper":"/paper/deep-model-predictive-optimization","title":"Deep Model Predictive Optimization","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jisacks/dmpo","path":"dmpo/experiment/experiment_utils.py","file_url":"https://github.com/jisacks/dmpo/blob/HEAD/dmpo/experiment/experiment_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e61855f98ff8786c","mcp_get_code":{"code_sha256":"e61855f98ff8786c"}},{"arxiv_id":"2106.02039","paper":"/paper/reinforcement-learning-as-one-big-sequence","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","date":"2021-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"howuhh/faster-trajectory-transformer","path":"trajectory/utils/env.py","file_url":"https://github.com/howuhh/faster-trajectory-transformer/blob/HEAD/trajectory/utils/env.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36bb7ea2ef4a54a3","mcp_get_code":{"code_sha256":"36bb7ea2ef4a54a3"}},{"arxiv_id":"2105.10389","paper":"/paper/learning-visible-connectivity-dynamics-for","title":"Learning Visible Connectivity Dynamics for Cloth Smoothing","date":"2021-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xingyu-Lin/VCD","path":"VCD/main_plan.py","file_url":"https://github.com/Xingyu-Lin/VCD/blob/HEAD/VCD/main_plan.py","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0e829e726d685205","mcp_get_code":{"code_sha256":"0e829e726d685205"}},{"arxiv_id":"2008.06319","paper":"/paper/or-gym-a-reinforcement-learning-library-for","title":"OR-Gym: A Reinforcement Learning Library for Operations Research Problems","date":"2020-08-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hubbs5/or-gym","path":"or_gym/utils.py","file_url":"https://github.com/hubbs5/or-gym/blob/HEAD/or_gym/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a231083fdbed8b87","mcp_get_code":{"code_sha256":"a231083fdbed8b87"}},{"arxiv_id":"1910.09066","paper":"/paper/from-importance-sampling-to-doubly-robust","title":"From Importance Sampling to Doubly Robust Policy Gradient","date":"2019-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Leonardo-H/DR-PG","path":"rl/envs/utils.py","file_url":"https://github.com/Leonardo-H/DR-PG/blob/HEAD/rl/envs/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":"635a39bd849996e1","mcp_get_code":{"code_sha256":"635a39bd849996e1"}},{"arxiv_id":"1810.06509","paper":"/paper/predictor-corrector-policy-optimization","title":"Predictor-Corrector Policy Optimization","date":"2018-10-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gtrll/rlfamily","path":"rl/envs/utils.py","file_url":"https://github.com/gtrll/rlfamily/blob/HEAD/rl/envs/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6b2980821d94e378","mcp_get_code":{"code_sha256":"6b2980821d94e378"}}]}