{"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/a-unified-approach-to-reinforcement-learning","title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","arxiv_id":"2206.05825","date":"2022-06-12","proceeding":null,"authors":["Samuel Sokota","Ryan D'Orazio","J. Zico Kolter","Nicolas Loizou","Marc Lanctot","Ioannis Mitliagkas","Noam Brown","Christian Kroer"],"abstract":"This work studies an algorithm, which we call magnetic mirror descent, that is inspired by mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is demonstrating the virtues of magnetic mirror descent as both an equilibrium solver and as an approach to reinforcement learning in two-player zero-sum games. These virtues include: 1) Being the first quantal response equilibria solver to achieve linear convergence for extensive-form games with first order feedback; 2) Being the first standard reinforcement learning algorithm to achieve empirically competitive results with CFR in tabular settings; 3) Achieving favorable performance in 3x3 Dark Hex and Phantom Tic-Tac-Toe as a self-play deep reinforcement learning algorithm.","url_abs":"https://arxiv.org/abs/2206.05825v4","url_pdf":"https://arxiv.org/pdf/2206.05825v4.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":"a-unified-approach-to-reinforcement-learning","repo_url":"https://github.com/deepmind/open_spiel","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"a-unified-approach-to-reinforcement-learning","repo_url":"https://github.com/ryan-dorazio/mmd-dilated","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"a-unified-approach-to-reinforcement-learning","repo_url":"https://github.com/ssokota/mmd","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"mujoco-games","task_name":"MuJoCo Games"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.05825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05825"}},"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/deepmind/open_spiel","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ryan-dorazio/mmd-dilated","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ssokota/mmd","reach":null}],"summary":{"ran_honours":1,"ran_violates":3,"ran_fixture":1},"by_repo_kind":{"named_in_paper":{"samples":5,"ran":5,"repositories":2}},"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":"65c22604836c3489","entry":"arbitrary","repo":"ssokota/mmd","repo_kind":"named_in_paper","path":"examples/h2h/evaluate.py","file_url":"https://github.com/ssokota/mmd/blob/HEAD/examples/h2h/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"65c22604836c3489"}},{"code_sha256_prefix":"5b9b7639a0244fd3","entry":"kl_divergence","repo":"ryan-dorazio/mmd-dilated","repo_kind":"named_in_paper","path":"mmd_dilated/mmd_dilated.py","file_url":"https://github.com/ryan-dorazio/mmd-dilated/blob/HEAD/mmd_dilated/mmd_dilated.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b9b7639a0244fd3"}},{"code_sha256_prefix":"bb891307b0169805","entry":"neg_entropy","repo":"ryan-dorazio/mmd-dilated","repo_kind":"named_in_paper","path":"mmd_dilated/mmd_dilated.py","file_url":"https://github.com/ryan-dorazio/mmd-dilated/blob/HEAD/mmd_dilated/mmd_dilated.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb891307b0169805"}},{"code_sha256_prefix":"01d9233798b0f630","entry":"random","repo":"ssokota/mmd","repo_kind":"named_in_paper","path":"examples/h2h/evaluate.py","file_url":"https://github.com/ssokota/mmd/blob/HEAD/examples/h2h/evaluate.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01d9233798b0f630"}},{"code_sha256_prefix":"50d5258bd0761c1b","entry":"softmax","repo":"ryan-dorazio/mmd-dilated","repo_kind":"named_in_paper","path":"mmd_dilated/mmd_dilated.py","file_url":"https://github.com/ryan-dorazio/mmd-dilated/blob/HEAD/mmd_dilated/mmd_dilated.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"50d5258bd0761c1b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}