{"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/learn","entry":"learn","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":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":8,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":6,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":8},"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":"2210.00066","paper":"/paper/improving-policy-learning-via-language","title":"Improving Policy Learning via Language Dynamics Distillation","date":"2022-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/nle","path":"nle/agent/agent.py","file_url":"https://github.com/facebookresearch/nle/blob/HEAD/nle/agent/agent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fa8a88fb35b3b6f6","mcp_get_code":{"code_sha256":"fa8a88fb35b3b6f6"}},{"arxiv_id":"2111.13119","paper":"/paper/interesting-object-curious-agent-learning-1","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","date":"2021-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sparisi/cbet","path":"src/algos/cbet.py","file_url":"https://github.com/sparisi/cbet/blob/HEAD/src/algos/cbet.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"9c51a8865771801c","mcp_get_code":{"code_sha256":"9c51a8865771801c"}},{"arxiv_id":"2106.06135","paper":"/paper/douzero-mastering-doudizhu-with-self-play","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","date":"2021-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Liberations/DouZero_For_HLDDZ_FullAuto","path":"douzero/dmc/dmc.py","file_url":"https://github.com/Liberations/DouZero_For_HLDDZ_FullAuto/blob/HEAD/douzero/dmc/dmc.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":"ee16d8c3495cc1e3","mcp_get_code":{"code_sha256":"ee16d8c3495cc1e3"}},{"arxiv_id":"2105.09992","paper":"/paper/don-t-do-what-doesn-t-matter-intrinsic","title":"Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness","date":"2021-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Mathieu-Seurin/impact-driven-exploration","path":"src/algos/ride.py","file_url":"https://github.com/Mathieu-Seurin/impact-driven-exploration/blob/HEAD/src/algos/ride.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"c96a61a23006629e","mcp_get_code":{"code_sha256":"c96a61a23006629e"}},{"arxiv_id":"1906.08754","paper":"/paper/learning-the-sampling-pattern-for-mri","title":"Learning the Sampling Pattern for MRI","date":"2019-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fsherry/bilevelmri","path":"bilevelmri/experiment_setup.py","file_url":"https://github.com/fsherry/bilevelmri/blob/HEAD/bilevelmri/experiment_setup.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"bece12f18ac7ad1c","mcp_get_code":{"code_sha256":"bece12f18ac7ad1c"}},{"arxiv_id":"1904.00370","paper":"/paper/variational-adversarial-active-learning","title":"Variational Adversarial Active Learning","date":"2019-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"johntiger1/vaal_querying","path":"rl/sample_cartpole.py","file_url":"https://github.com/johntiger1/vaal_querying/blob/HEAD/rl/sample_cartpole.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"code_sha256_prefix":"c770702517776776","mcp_get_code":{"code_sha256":"c770702517776776"}},{"arxiv_id":"1809.03470","paper":"/paper/vizdoom-competitions-playing-doom-from-pixels","title":"ViZDoom Competitions: Playing Doom from Pixels","date":"2018-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hegde95/ViZDoom_with_Sound","path":"examples/python/learning_pytorch.py","file_url":"https://github.com/hegde95/ViZDoom_with_Sound/blob/HEAD/examples/python/learning_pytorch.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c49e869676fa9a5f","mcp_get_code":{"code_sha256":"c49e869676fa9a5f"}},{"arxiv_id":"1707.06347","paper":"/paper/proximal-policy-optimization-algorithms","title":"Proximal Policy Optimization Algorithms","date":"2017-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangzhengfei0730/NIPS2018-AIforProsthetics","path":"baselines/ppo2/ppo2.py","file_url":"https://github.com/wangzhengfei0730/NIPS2018-AIforProsthetics/blob/HEAD/baselines/ppo2/ppo2.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"be674cc9da531aa5","mcp_get_code":{"code_sha256":"be674cc9da531aa5"}},{"arxiv_id":"1605.02097","paper":"/paper/vizdoom-a-doom-based-ai-research-platform-for","title":"ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning","date":"2016-05-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"c49e869676fa9a5f","mcp_get_code":{"code_sha256":"c49e869676fa9a5f"}}]}