{"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/diaggaussianactor","entry":"DiagGaussianActor","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":5,"n_papers_ran":5,"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":5,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":0},"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":"2605.01242","paper":"/paper/arxiv-2605-01242","title":"Breaking the Computational Barrier: Provably Efficient Actor-Critic for Low-Rank MDPs","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"shelowize/lvrep-rl","path":"agent/ctrlsac/ctrlsac_agent.py","file_url":"https://github.com/shelowize/lvrep-rl/blob/HEAD/agent/ctrlsac/ctrlsac_agent.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0af1491833d134ca","mcp_get_code":{"code_sha256":"0af1491833d134ca"}},{"arxiv_id":"2412.05675","paper":"/paper/m-3-pc-test-time-model-predictive-control-for","title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","date":"2024-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wkh923/m3pc","path":"research/omtm/models/mtm_model.py","file_url":"https://github.com/wkh923/m3pc/blob/HEAD/research/omtm/models/mtm_model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"a869371c3b82ecd1","mcp_get_code":{"code_sha256":"a869371c3b82ecd1"}},{"arxiv_id":"2302.07351","paper":"/paper/constrained-decision-transformer-for-offline","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","date":"2023-02-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuzuxin/osrl","path":"osrl/algorithms/cdt.py","file_url":"https://github.com/liuzuxin/osrl/blob/HEAD/osrl/algorithms/cdt.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"be40c78e1e5f43e3","mcp_get_code":{"code_sha256":"be40c78e1e5f43e3"}},{"arxiv_id":"2110.06169","paper":"/paper/offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"orrivlin/implicit-q-learning","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"96a8264069e38c3a","mcp_get_code":{"code_sha256":"96a8264069e38c3a"}},{"arxiv_id":"1611.02779","paper":"/paper/rl2-fast-reinforcement-learning-via-slow","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","date":"2016-11-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aliengirlliv/teachable","path":"algos/ppo.py","file_url":"https://github.com/aliengirlliv/teachable/blob/HEAD/algos/ppo.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"11487404dfdc69d8","mcp_get_code":{"code_sha256":"11487404dfdc69d8"}}]}