{"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/guarantees-for-self-play-in-multiplayer-games","title":"Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability","arxiv_id":"2310.11518","date":"2023-10-17","proceeding":"NeurIPS 2023 11","authors":["Revan MacQueen","James R. Wright"],"abstract":"Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that the agents the learner will face post-training may have dramatically different behavior than the learner came to expect by interacting with itself. For the special case of two-player constant-sum games, self-play that reaches Nash equilibrium is guaranteed to produce strategies that perform well against any post-training opponent; however, no such guarantee exists for multiplayer games. We show that in games that approximately decompose into a set of two-player constant-sum games (called constant-sum polymatrix games) where global $\\epsilon$-Nash equilibria are boundedly far from Nash equilibria in each subgame (called subgame stability), any no-external-regret algorithm that learns by self-play will produce a strategy with bounded vulnerability. For the first time, our results identify a structural property of multiplayer games that enable performance guarantees for the strategies produced by a broad class of self-play algorithms. We demonstrate our findings through experiments on Leduc poker.","url_abs":"https://arxiv.org/abs/2310.11518v3","url_pdf":"https://arxiv.org/pdf/2310.11518v3.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":"guarantees-for-self-play-in-multiplayer-games","repo_url":"https://github.com/revanmacqueen/self-play-polymatrix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.11518","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11518"}},"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/revanmacqueen/self-play-polymatrix","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":7},"by_repo_kind":{"official":{"samples":9,"ran":2,"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":"6a1b94b9673edebf","entry":"sample_strats","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/sgdecompose_utils.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/sgdecompose_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6a1b94b9673edebf"}},{"code_sha256_prefix":"28af04455767e75f","entry":"unique","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/sequence.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/sequence.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"28af04455767e75f"}},{"code_sha256_prefix":"a4f6acece04d00f9","entry":"chance_terminal_reach_probs","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/terminals.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/terminals.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4f6acece04d00f9"}},{"code_sha256_prefix":"841c6361af5f151b","entry":"construct_vars","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/sequence.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/sequence.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"841c6361af5f151b"}},{"code_sha256_prefix":"1d23d239a4db1528","entry":"get_terminal_returns","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/terminals.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/terminals.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d23d239a4db1528"}},{"code_sha256_prefix":"73a391bea90ed36d","entry":"is_root","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/sequence.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/sequence.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73a391bea90ed36d"}},{"code_sha256_prefix":"47a480a6d65cdd35","entry":"player_terminal_reach","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/terminals.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/terminals.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47a480a6d65cdd35"}},{"code_sha256_prefix":"32d3351455213744","entry":"tree_norm","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/sgdecompose_utils.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/sgdecompose_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32d3351455213744"}},{"code_sha256_prefix":"e1a9347c7cfb64de","entry":"tree_normalize","repo":"revanmacqueen/self-play-polymatrix","repo_kind":"official","path":"sgdecompose/sgdecompose_utils.py","file_url":"https://github.com/revanmacqueen/self-play-polymatrix/blob/HEAD/sgdecompose/sgdecompose_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e1a9347c7cfb64de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}