{"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/magic-box","entry":"magic_box","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":3,"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":2,"n_samples_fingerprinted":2,"n_places":8,"n_places_pointer_only":1,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":1,"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":"2210.10125","paper":"/paper/proximal-learning-with-opponent-learning","title":"Proximal Learning With Opponent-Learning Awareness","date":"2022-10-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"silent-zebra/pola","path":"jax_files/POLA_dice_jax.py","file_url":"https://github.com/silent-zebra/pola/blob/HEAD/jax_files/POLA_dice_jax.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f4166f1f2230b2e7","mcp_get_code":{"code_sha256":"f4166f1f2230b2e7"}},{"arxiv_id":"2112.15400","paper":"/paper/settling-the-bias-and-variance-of-meta","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","date":"2021-12-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"2d97875446464dc6","mcp_get_code":{"code_sha256":"2d97875446464dc6"}},{"arxiv_id":"2105.13524","paper":"/paper/improving-generalization-in-meta-rl-with","title":"Improving Generalization in Meta-RL with Imaginary Tasks from Latent Dynamics Mixture","date":"2021-05-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jonasrothfuss/ProMP","path":"meta_policy_search/meta_algos/dice_maml.py","file_url":"https://github.com/jonasrothfuss/ProMP/blob/HEAD/meta_policy_search/meta_algos/dice_maml.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a384fd2f6407795c","mcp_get_code":{"code_sha256":"a384fd2f6407795c"}},{"arxiv_id":"2011.00382","paper":"/paper/a-policy-gradient-algorithm-for-learning-to-1","title":"A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning","date":"2020-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dkkim93/meta-mapg","path":"meta/dice.py","file_url":"https://github.com/dkkim93/meta-mapg/blob/HEAD/meta/dice.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"17699ef2e449301d","mcp_get_code":{"code_sha256":"17699ef2e449301d"}},{"arxiv_id":"1810.06784","paper":"/paper/promp-proximal-meta-policy-search","title":"ProMP: Proximal Meta-Policy Search","date":"2018-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jonasrothfuss/promp","path":"meta_policy_search/meta_algos/dice_maml.py","file_url":"https://github.com/jonasrothfuss/promp/blob/HEAD/meta_policy_search/meta_algos/dice_maml.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a384fd2f6407795c","mcp_get_code":{"code_sha256":"a384fd2f6407795c"}},{"arxiv_id":"1709.04326","paper":"/paper/learning-with-opponent-learning-awareness","title":"Learning with Opponent-Learning Awareness","date":"2017-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"alexis-jacq/LOLA_DICE","path":"ipd_DiCE.py","file_url":"https://github.com/alexis-jacq/LOLA_DICE/blob/HEAD/ipd_DiCE.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"2d97875446464dc6","mcp_get_code":{"code_sha256":"2d97875446464dc6"}},{"arxiv_id":"1703.03400","paper":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iclavera/meta-mb","path":"meta_mb/meta_algos/dice_maml.py","file_url":"https://github.com/iclavera/meta-mb/blob/HEAD/meta_mb/meta_algos/dice_maml.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a384fd2f6407795c","mcp_get_code":{"code_sha256":"a384fd2f6407795c"}},{"arxiv_id":"1703.03400","paper":"/paper/model-agnostic-meta-learning-for-fast","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","date":"2017-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"iclavera/meta-mb","path":"meta_mb/meta_algos/dice_maml_xtra_bl.py","file_url":"https://github.com/iclavera/meta-mb/blob/HEAD/meta_mb/meta_algos/dice_maml_xtra_bl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a59b5aa3c2e6207","mcp_get_code":{"code_sha256":"4a59b5aa3c2e6207"}}]}