{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:PMOC2ZDA7DA26M2GEWIVAQAGC6","short_pith_number":"pith:PMOC2ZDA","schema_version":"1.0","canonical_sha256":"7b1c2d6460f8c1af334625915040061786660c2361055ef35594dc5d77d3b631","source":{"kind":"arxiv","id":"1411.7974","version":2},"attestation_state":"computed","paper":{"title":"Solving Games with Functional Regret Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Dustin Morrill, J. Andrew Bagnell, Kevin Waugh, Michael Bowling","submitted_at":"2014-11-28T18:45:50Z","abstract_excerpt":"We propose a novel online learning method for minimizing regret in large extensive-form games. The approach learns a function approximator online to estimate the regret for choosing a particular action. A no-regret algorithm uses these estimates in place of the true regrets to define a sequence of policies.\n  We prove the approach sound by providing a bound relating the quality of the function approximation and regret of the algorithm. A corollary being that the method is guaranteed to converge to a Nash equilibrium in self-play so long as the regrets are ultimately realizable by the function "},"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":"1411.7974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-11-28T18:45:50Z","cross_cats_sorted":["cs.GT","cs.MA"],"title_canon_sha256":"91d2ad1b6526c6e5373c23be6fe00ce9451b7ae627f94b0d25fdb923bf44ecc2","abstract_canon_sha256":"2c0bbfbf0dcd61f6c9ca2e422eb5ae6519aa78e3f7f3fc6aed473759b72f4956"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:30:15.171128Z","signature_b64":"Jx56HIEqh8eaPeXZEJQ5y8GoyQVhKyQi1U5GIunCpBpdSP4xJsl9+A87iGo10V5j1WWlqhh0DhvUST7kjaRRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b1c2d6460f8c1af334625915040061786660c2361055ef35594dc5d77d3b631","last_reissued_at":"2026-05-18T02:30:15.170668Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:30:15.170668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Games with Functional Regret Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.AI","authors_text":"Dustin Morrill, J. Andrew Bagnell, Kevin Waugh, Michael Bowling","submitted_at":"2014-11-28T18:45:50Z","abstract_excerpt":"We propose a novel online learning method for minimizing regret in large extensive-form games. The approach learns a function approximator online to estimate the regret for choosing a particular action. A no-regret algorithm uses these estimates in place of the true regrets to define a sequence of policies.\n  We prove the approach sound by providing a bound relating the quality of the function approximation and regret of the algorithm. A corollary being that the method is guaranteed to converge to a Nash equilibrium in self-play so long as the regrets are ultimately realizable by the function "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.7974","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1411.7974","created_at":"2026-05-18T02:30:15.170737+00:00"},{"alias_kind":"arxiv_version","alias_value":"1411.7974v2","created_at":"2026-05-18T02:30:15.170737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.7974","created_at":"2026-05-18T02:30:15.170737+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMOC2ZDA7DA2","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMOC2ZDA7DA26M2G","created_at":"2026-05-18T12:28:43.426989+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMOC2ZDA","created_at":"2026-05-18T12:28:43.426989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6","json":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6.json","graph_json":"https://pith.science/api/pith-number/PMOC2ZDA7DA26M2GEWIVAQAGC6/graph.json","events_json":"https://pith.science/api/pith-number/PMOC2ZDA7DA26M2GEWIVAQAGC6/events.json","paper":"https://pith.science/paper/PMOC2ZDA"},"agent_actions":{"view_html":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6","download_json":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6.json","view_paper":"https://pith.science/paper/PMOC2ZDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1411.7974&json=true","fetch_graph":"https://pith.science/api/pith-number/PMOC2ZDA7DA26M2GEWIVAQAGC6/graph.json","fetch_events":"https://pith.science/api/pith-number/PMOC2ZDA7DA26M2GEWIVAQAGC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6/action/storage_attestation","attest_author":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6/action/author_attestation","sign_citation":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6/action/citation_signature","submit_replication":"https://pith.science/pith/PMOC2ZDA7DA26M2GEWIVAQAGC6/action/replication_record"}},"created_at":"2026-05-18T02:30:15.170737+00:00","updated_at":"2026-05-18T02:30:15.170737+00:00"}