{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NBSLF4B4K5TH6EL6SX5R2HID3O","short_pith_number":"pith:NBSLF4B4","schema_version":"1.0","canonical_sha256":"6864b2f03c57667f117e95fb1d1d03dba78344d8b7d011abbd29ba2faf56063b","source":{"kind":"arxiv","id":"2402.11835","version":1},"attestation_state":"computed","paper":{"title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"David C. Parkes, Hugh Zhang, Luca D'Amico-Wong, Marc Lanctot","submitted_at":"2024-02-19T04:58:39Z","abstract_excerpt":"We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm for single-agent domains, and counterfactual regret minimization (CFR), a central algorithm for learning in multi-agent domains. ABCs adaptively chooses what fraction of the environment to explore each iteration by measuring the stationarity of the environment's reward and transition dynamics. In Markov decision processes, ABCs converges to the optimal policy with at most an O(A) factor slowdown compared to BQL, where "},"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":"2402.11835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-19T04:58:39Z","cross_cats_sorted":["cs.GT","cs.MA"],"title_canon_sha256":"49252d4c8f2297de00a3a6eba0799987f16c462c391f2a14b13d9bce14dafe34","abstract_canon_sha256":"b391c556757ba168a045ff5c50f22df2ab3d6d529e8598e6fddcc1fed3414bb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:45.066136Z","signature_b64":"u2pzEQyBYJp0cSdQ1i2dSTO1ZxU/1z1SyM7frcIm1ZpUafef6VB47aqqeBvW3nsHaMrWBhhTBu4NxbTwGGtRBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6864b2f03c57667f117e95fb1d1d03dba78344d8b7d011abbd29ba2faf56063b","last_reissued_at":"2026-07-05T07:46:45.065793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:45.065793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.MA"],"primary_cat":"cs.LG","authors_text":"David C. Parkes, Hugh Zhang, Luca D'Amico-Wong, Marc Lanctot","submitted_at":"2024-02-19T04:58:39Z","abstract_excerpt":"We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm for single-agent domains, and counterfactual regret minimization (CFR), a central algorithm for learning in multi-agent domains. ABCs adaptively chooses what fraction of the environment to explore each iteration by measuring the stationarity of the environment's reward and transition dynamics. In Markov decision processes, ABCs converges to the optimal policy with at most an O(A) factor slowdown compared to BQL, where "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11835","kind":"arxiv","version":1},"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/2402.11835/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":"2402.11835","created_at":"2026-07-05T07:46:45.065849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11835v1","created_at":"2026-07-05T07:46:45.065849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11835","created_at":"2026-07-05T07:46:45.065849+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBSLF4B4K5TH","created_at":"2026-07-05T07:46:45.065849+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBSLF4B4K5TH6EL6","created_at":"2026-07-05T07:46:45.065849+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBSLF4B4","created_at":"2026-07-05T07:46:45.065849+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/NBSLF4B4K5TH6EL6SX5R2HID3O","json":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O.json","graph_json":"https://pith.science/api/pith-number/NBSLF4B4K5TH6EL6SX5R2HID3O/graph.json","events_json":"https://pith.science/api/pith-number/NBSLF4B4K5TH6EL6SX5R2HID3O/events.json","paper":"https://pith.science/paper/NBSLF4B4"},"agent_actions":{"view_html":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O","download_json":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O.json","view_paper":"https://pith.science/paper/NBSLF4B4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11835&json=true","fetch_graph":"https://pith.science/api/pith-number/NBSLF4B4K5TH6EL6SX5R2HID3O/graph.json","fetch_events":"https://pith.science/api/pith-number/NBSLF4B4K5TH6EL6SX5R2HID3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/action/storage_attestation","attest_author":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/action/author_attestation","sign_citation":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/action/citation_signature","submit_replication":"https://pith.science/pith/NBSLF4B4K5TH6EL6SX5R2HID3O/action/replication_record"}},"created_at":"2026-07-05T07:46:45.065849+00:00","updated_at":"2026-07-05T07:46:45.065849+00:00"}