{"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/compute-gae","entry":"compute_gae","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":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":6,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":1,"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":"2601.17563","paper":"/paper/arxiv-2601-17563","title":"Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"NathanGavenski/UfO","path":"utils/utils.py","file_url":"https://github.com/NathanGavenski/UfO/blob/HEAD/utils/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ac490b99b2e1f91d","mcp_get_code":{"code_sha256":"ac490b99b2e1f91d"}},{"arxiv_id":"2511.21848","paper":"/paper/arxiv-2511-21848","title":"Massively Parallel Imitation Learning of Mouse Forelimb Musculoskeletal Reaching Dynamics","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"talmolab/track-mjx","path":"track_mjx/agent/ff_ppo/losses.py","file_url":"https://github.com/talmolab/track-mjx/blob/HEAD/track_mjx/agent/ff_ppo/losses.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"edd567b15d0b6be9","mcp_get_code":{"code_sha256":"edd567b15d0b6be9"}},{"arxiv_id":"2402.12284","paper":"/paper/refining-minimax-regret-for-unsupervised","title":"Refining Minimax Regret for Unsupervised Environment Design","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"michael-beukman/remidi","path":"lib/common/ppo.py","file_url":"https://github.com/michael-beukman/remidi/blob/HEAD/lib/common/ppo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f20aa0108a055874","mcp_get_code":{"code_sha256":"f20aa0108a055874"}},{"arxiv_id":"2311.11385","paper":"/paper/multi-task-reinforcement-learning-with-1","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","date":"2023-11-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"AhmedMagdyHendawy/MOORE","path":"moore/algorithms/actor_critic/deep_actor_critic/mtppo.py","file_url":"https://github.com/AhmedMagdyHendawy/MOORE/blob/HEAD/moore/algorithms/actor_critic/deep_actor_critic/mtppo.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f099922845e9053f","mcp_get_code":{"code_sha256":"f099922845e9053f"}},{"arxiv_id":"2212.02098","paper":"/paper/a-machine-with-short-term-episodic-and","title":"A Machine with Short-Term, Episodic, and Semantic Memory Systems","date":"2022-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"humemai/agent-room-env-v1","path":"agent/ppo/utils.py","file_url":"https://github.com/humemai/agent-room-env-v1/blob/HEAD/agent/ppo/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"095f68d3628f0df1","mcp_get_code":{"code_sha256":"095f68d3628f0df1"}},{"arxiv_id":"2202.04332","paper":"/paper/imitation-learning-by-state-only-distribution","title":"Imitation Learning by State-Only Distribution Matching","date":"2022-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FeMa42/soil-tdm","path":"gym_exp_data.py","file_url":"https://github.com/FeMa42/soil-tdm/blob/HEAD/gym_exp_data.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"39dd7febc8e9fb8f","mcp_get_code":{"code_sha256":"39dd7febc8e9fb8f"}}]}