{"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/tanhgaussianpolicy","entry":"TanhGaussianPolicy","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":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":6,"n_samples_ran":5,"n_samples_fingerprinted":4,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":5,"unverified":1},"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":"2605.05863","paper":"/paper/arxiv-2605-05863","title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"CarloRomeo427/SOPE","path":"src/algos/agent_sope.py","file_url":"https://github.com/CarloRomeo427/SOPE/blob/HEAD/src/algos/agent_sope.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ce08a4d7af866e17","mcp_get_code":{"code_sha256":"ce08a4d7af866e17"}},{"arxiv_id":"2405.17477","paper":"/paper/ollie-imitation-learning-from-offline","title":"OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning","date":"2024-05-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hansenhua/ollie-offline-to-online-imitation-learning","path":"offline_to_online.py","file_url":"https://github.com/hansenhua/ollie-offline-to-online-imitation-learning/blob/HEAD/offline_to_online.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e4002bdf5440538b","mcp_get_code":{"code_sha256":"e4002bdf5440538b"}},{"arxiv_id":"2312.02019","paper":"/paper/action-inference-by-maximising-evidence-zero-1","title":"Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models","date":"2023-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"argmax-ai/aime","path":"aime/models/ssm.py","file_url":"https://github.com/argmax-ai/aime/blob/HEAD/aime/models/ssm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"802c8c98d4863016","mcp_get_code":{"code_sha256":"802c8c98d4863016"}},{"arxiv_id":"2207.10050","paper":"/paper/discriminator-weighted-offline-imitation-1","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","date":"2022-07-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zexusun/oilca-neurips23","path":"algos/augment_DWBC.py","file_url":"https://github.com/zexusun/oilca-neurips23/blob/HEAD/algos/augment_DWBC.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7c13f96c95dad29","mcp_get_code":{"code_sha256":"a7c13f96c95dad29"}},{"arxiv_id":"2110.02034","paper":"/paper/dropout-q-functions-for-doubly-efficient","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","date":"2021-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"watchernyu/REDQ","path":"redq/algos/redq_sac.py","file_url":"https://github.com/watchernyu/REDQ/blob/HEAD/redq/algos/redq_sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"5fb36a006ce8ed7c","mcp_get_code":{"code_sha256":"5fb36a006ce8ed7c"}},{"arxiv_id":"2101.05982","paper":"/paper/randomized-ensembled-double-q-learning-1","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","date":"2021-01-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ustcmike/adaeq_neurips21","path":"redq/algos/redq_sac.py","file_url":"https://github.com/ustcmike/adaeq_neurips21/blob/HEAD/redq/algos/redq_sac.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"1172d63a1c99206d","mcp_get_code":{"code_sha256":"1172d63a1c99206d"}}]}