{"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/find-task-for-env-id-in-any-benchmark","entry":"find_task_for_env_id_in_any_benchmark","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":0,"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":3,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":3},"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":"2206.06614","paper":"/paper/transformers-are-meta-reinforcement-learners-1","title":"Transformers are Meta-Reinforcement Learners","date":"2022-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luckeciano/transformers-metarl","path":"benchmarks/src/garage_benchmarks/benchmarks.py","file_url":"https://github.com/luckeciano/transformers-metarl/blob/HEAD/benchmarks/src/garage_benchmarks/benchmarks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"286b82196c4fe36b","mcp_get_code":{"code_sha256":"286b82196c4fe36b"}},{"arxiv_id":"2006.04061","paper":"/paper/dual-policy-distillation","title":"Dual Policy Distillation","date":"2020-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kiminh/dual-policy-distillation","path":"baselines/bench/benchmarks.py","file_url":"https://github.com/kiminh/dual-policy-distillation/blob/HEAD/baselines/bench/benchmarks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"71bdb8bae1ed81f7","mcp_get_code":{"code_sha256":"71bdb8bae1ed81f7"}},{"arxiv_id":"2001.03415","paper":"/paper/multi-agent-interactions-modeling-with-1","title":"Multi-Agent Interactions Modeling with Correlated Policies","date":"2020-01-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apexrl/codail","path":"multi-agent-irl/rl/bench/benchmarks.py","file_url":"https://github.com/apexrl/codail/blob/HEAD/multi-agent-irl/rl/bench/benchmarks.py","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"97c4da6e50f18d58","mcp_get_code":{"code_sha256":"97c4da6e50f18d58"}},{"arxiv_id":"1905.02363","paper":"/paper/dimension-wise-importance-sampling-weight","title":"Dimension-Wise Importance Sampling Weight Clipping for Sample-Efficient Reinforcement Learning","date":"2019-05-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seungyulhan/disc","path":"baselines/bench/benchmarks.py","file_url":"https://github.com/seungyulhan/disc/blob/HEAD/baselines/bench/benchmarks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"71bdb8bae1ed81f7","mcp_get_code":{"code_sha256":"71bdb8bae1ed81f7"}},{"arxiv_id":"1606.03476","paper":"/paper/generative-adversarial-imitation-learning","title":"Generative Adversarial Imitation Learning","date":"2016-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Techget/gail-tf-sc2","path":"gailtf/baselines/bench/benchmarks.py","file_url":"https://github.com/Techget/gail-tf-sc2/blob/HEAD/gailtf/baselines/bench/benchmarks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"71bdb8bae1ed81f7","mcp_get_code":{"code_sha256":"71bdb8bae1ed81f7"}},{"arxiv_id":"1604.06778","paper":"/paper/benchmarking-deep-reinforcement-learning-for","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","date":"2016-04-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rlworkgroup/garage","path":"benchmarks/src/garage_benchmarks/benchmarks.py","file_url":"https://github.com/rlworkgroup/garage/blob/HEAD/benchmarks/src/garage_benchmarks/benchmarks.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"286b82196c4fe36b","mcp_get_code":{"code_sha256":"286b82196c4fe36b"}}]}