{"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-deep-reinforcement-learning-approach-for-13","title":"A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games","arxiv_id":"2207.08894","date":"2022-07-18","proceeding":null,"authors":["Zihan Ding","DiJia Su","Qinghua Liu","Chi Jin"],"abstract":"This paper proposes new, end-to-end deep reinforcement learning algorithms for learning two-player zero-sum Markov games. Different from prior efforts on training agents to beat a fixed set of opponents, our objective is to find the Nash equilibrium policies that are free from exploitation by even the adversarial opponents. We propose (a) Nash-DQN algorithm, which integrates the deep learning techniques from single DQN into the classic Nash Q-learning algorithm for solving tabular Markov games; (b) Nash-DQN-Exploiter algorithm, which additionally adopts an exploiter to guide the exploration of the main agent. We conduct experimental evaluation on tabular examples as well as various two-player Atari games. Our empirical results demonstrate that (i) the policies found by many existing methods including Neural Fictitious Self Play and Policy Space Response Oracle can be prone to exploitation by adversarial opponents; (ii) the output policies of our algorithms are robust to exploitation, and thus outperform existing methods.","url_abs":"https://arxiv.org/abs/2207.08894v3","url_pdf":"https://arxiv.org/pdf/2207.08894v3.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-deep-reinforcement-learning-approach-for-13","repo_url":"https://github.com/quantumiracle/mars","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-deep-reinforcement-learning-approach-for-13","repo_url":"https://github.com/quantumiracle/nash-dqn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"q-learning","task_name":"Q-Learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.08894","atlas_url":"https://app.syntology.ai/?focus=2207.08894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08894"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/quantumiracle/nash-dqn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/quantumiracle/mars","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":5,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":"81e21540e0757e7b","entry":"NashEquilibriumCVXPYSolver","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/eq_CVXPYsolver.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/eq_CVXPYsolver.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81e21540e0757e7b"}},{"code_sha256_prefix":"50b1e533c45c2ec3","entry":"arrayWithoutElement","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/gamegenerator.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/gamegenerator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50b1e533c45c2ec3"}},{"code_sha256_prefix":"1e9c1d4bf7ca8df8","entry":"cartesian","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/gamegenerator.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/gamegenerator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e9c1d4bf7ca8df8"}},{"code_sha256_prefix":"f03da9b695af9788","entry":"get_payoff_vector","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/eq_MWUsolver.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/eq_MWUsolver.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f03da9b695af9788"}},{"code_sha256_prefix":"90d75e71673e0ce9","entry":"parseGame","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/gamegenerator.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/gamegenerator.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90d75e71673e0ce9"}},{"code_sha256_prefix":"250b4ac1fe45568c","entry":"CoarseCorrelatedEquilibriumLPSolver","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/eq_LPsolver.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/eq_LPsolver.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"250b4ac1fe45568c"}},{"code_sha256_prefix":"a3d4bff369d05675","entry":"NashEquilibriumLPSolver","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/eq_LPsolver.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/eq_LPsolver.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a3d4bff369d05675"}},{"code_sha256_prefix":"7ce310a0a27122d0","entry":"NashEquilibriumMWUSolver","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/eq_MWUsolver.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/eq_MWUsolver.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7ce310a0a27122d0"}},{"code_sha256_prefix":"e5fe2f8ec0681121","entry":"NashEquilibriumParallelMWUSolver","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/equilibrium_solver/eq_MWUsolver.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/equilibrium_solver/eq_MWUsolver.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e5fe2f8ec0681121"}},{"code_sha256_prefix":"7bd11d0025602c10","entry":"make_env","repo":"quantumiracle/mars","repo_kind":"official","path":"mars/env/import_env.py","file_url":"https://github.com/quantumiracle/mars/blob/HEAD/mars/env/import_env.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7bd11d0025602c10"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}