{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M23IBZMZQQPIJFWYP4UTWYLJBW","short_pith_number":"pith:M23IBZMZ","schema_version":"1.0","canonical_sha256":"66b680e599841e8496d87f293b61690d8c607f8fdeee4b7ae0b963125debd06d","source":{"kind":"arxiv","id":"2206.05825","version":4},"attestation_state":"computed","paper":{"title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Christian Kroer, Ioannis Mitliagkas, J. Zico Kolter, Marc Lanctot, Nicolas Loizou, Noam Brown, Ryan D'Orazio, Samuel Sokota","submitted_at":"2022-06-12T19:49:14Z","abstract_excerpt":"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 wi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.05825","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-12T19:49:14Z","cross_cats_sorted":["cs.AI","cs.GT"],"title_canon_sha256":"1c27af183688c48af14ae26f59f32a65b2613767fd73f873ba5bbdee82d17877","abstract_canon_sha256":"1f35c61465cf94de29739af499494d968e43d932edd5b9de1a24e72eb9aeca68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:33.900569Z","signature_b64":"zIdSGiBBS7p9BXI5JuzEpPXjCfMpb6dK1S/U8R8kJ3tvZVA1XG/75keAQzt3pwT/yYvZuHzKf/5BIILjsDO2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66b680e599841e8496d87f293b61690d8c607f8fdeee4b7ae0b963125debd06d","last_reissued_at":"2026-07-05T05:59:33.900120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:33.900120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT"],"primary_cat":"cs.LG","authors_text":"Christian Kroer, Ioannis Mitliagkas, J. Zico Kolter, Marc Lanctot, Nicolas Loizou, Noam Brown, Ryan D'Orazio, Samuel Sokota","submitted_at":"2022-06-12T19:49:14Z","abstract_excerpt":"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 wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05825","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.05825/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.05825","created_at":"2026-07-05T05:59:33.900177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.05825v4","created_at":"2026-07-05T05:59:33.900177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05825","created_at":"2026-07-05T05:59:33.900177+00:00"},{"alias_kind":"pith_short_12","alias_value":"M23IBZMZQQPI","created_at":"2026-07-05T05:59:33.900177+00:00"},{"alias_kind":"pith_short_16","alias_value":"M23IBZMZQQPIJFWY","created_at":"2026-07-05T05:59:33.900177+00:00"},{"alias_kind":"pith_short_8","alias_value":"M23IBZMZ","created_at":"2026-07-05T05:59:33.900177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06514","citing_title":"FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2606.28308","citing_title":"Which Nash Equilibrium? Solver-Dependent Selection on Zero-Sum Nash Polytopes","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29457","citing_title":"How Much Due Diligence Before You Bid? Learning in Intractable Takeover Auctions","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19235","citing_title":"GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23102","citing_title":"Multiplayer Nash Preference Optimization","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2511.03724","citing_title":"Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW","json":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW.json","graph_json":"https://pith.science/api/pith-number/M23IBZMZQQPIJFWYP4UTWYLJBW/graph.json","events_json":"https://pith.science/api/pith-number/M23IBZMZQQPIJFWYP4UTWYLJBW/events.json","paper":"https://pith.science/paper/M23IBZMZ"},"agent_actions":{"view_html":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW","download_json":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW.json","view_paper":"https://pith.science/paper/M23IBZMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.05825&json=true","fetch_graph":"https://pith.science/api/pith-number/M23IBZMZQQPIJFWYP4UTWYLJBW/graph.json","fetch_events":"https://pith.science/api/pith-number/M23IBZMZQQPIJFWYP4UTWYLJBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW/action/storage_attestation","attest_author":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW/action/author_attestation","sign_citation":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW/action/citation_signature","submit_replication":"https://pith.science/pith/M23IBZMZQQPIJFWYP4UTWYLJBW/action/replication_record"}},"created_at":"2026-07-05T05:59:33.900177+00:00","updated_at":"2026-07-05T05:59:33.900177+00:00"}