{"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":"/paper/muesli-combining-improvements-in-policy","title":"Muesli: Combining Improvements in Policy Optimization","arxiv_id":"2104.06159","date":"2021-04-13","proceeding":null,"authors":["Matteo Hessel","Ivo Danihelka","Fabio Viola","Arthur Guez","Simon Schmitt","Laurent SIfre","Theophane Weber","David Silver","Hado van Hasselt"],"abstract":"We propose a novel policy update that combines regularized policy optimization with model learning as an auxiliary loss. The update (henceforth Muesli) matches MuZero's state-of-the-art performance on Atari. Notably, Muesli does so without using deep search: it acts directly with a policy network and has computation speed comparable to model-free baselines. The Atari results are complemented by extensive ablations, and by additional results on continuous control and 9x9 Go.","url_abs":"https://arxiv.org/abs/2104.06159v2","url_pdf":"https://arxiv.org/pdf/2104.06159v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"muesli-combining-improvements-in-policy","repo_url":"https://github.com/Itomigna2/Muesli-lunarlander","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"muesli-combining-improvements-in-policy","repo_url":"https://github.com/YuriCat/MuesliJupyterExample","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atari-games-on-atari-game","task":"Atari Games","dataset":"atari game","model":"Muesli","rank_in_archive_order":8,"of":9,"metrics":{"Human World Record Breakthrough":"5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.06159","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.06159"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YuriCat/MuesliJupyterExample","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Itomigna2/Muesli-lunarlander","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2dad29e46e1d9e83","entry":"conv3x3","repo":"Itomigna2/Muesli-lunarlander","repo_kind":"listed","path":"Muesli_lunar_rgb.py","file_url":"https://github.com/Itomigna2/Muesli-lunarlander/blob/HEAD/Muesli_lunar_rgb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2dad29e46e1d9e83"}},{"code_sha256_prefix":"0da0f4c833bc9bdc","entry":"min_max_norm","repo":"Itomigna2/Muesli-lunarlander","repo_kind":"listed","path":"Muesli_lunar_rgb.py","file_url":"https://github.com/Itomigna2/Muesli-lunarlander/blob/HEAD/Muesli_lunar_rgb.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0da0f4c833bc9bdc"}},{"code_sha256_prefix":"4176db507b78ad31","entry":"mlp_proj","repo":"Itomigna2/Muesli-lunarlander","repo_kind":"listed","path":"Muesli_lunar_rgb.py","file_url":"https://github.com/Itomigna2/Muesli-lunarlander/blob/HEAD/Muesli_lunar_rgb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4176db507b78ad31"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}