{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5EJZQJTRUN5ZPGQBKWNJU33NL3","short_pith_number":"pith:5EJZQJTR","schema_version":"1.0","canonical_sha256":"e913982671a37b979a01559a9a6f6d5ee9eb6baef18985f5b00acb03375f845b","source":{"kind":"arxiv","id":"1809.03057","version":1},"attestation_state":"computed","paper":{"title":"Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games using Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GT","authors_text":"Marc Lanctot, Martin Schmid, Matej Moravcik, Michael Bowling, Neil Burch, Rudolf Kadlec","submitted_at":"2018-09-09T23:03:54Z","abstract_excerpt":"Learning strategies for imperfect information games from samples of interaction is a challenging problem. A common method for this setting, Monte Carlo Counterfactual Regret Minimization (MCCFR), can have slow long-term convergence rates due to high variance. In this paper, we introduce a variance reduction technique (VR-MCCFR) that applies to any sampling variant of MCCFR. Using this technique, per-iteration estimated values and updates are reformulated as a function of sampled values and state-action baselines, similar to their use in policy gradient reinforcement learning. The new formulati"},"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":"1809.03057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2018-09-09T23:03:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8870f4b1f63058bb1123a43685d3dc79f0631e4c6add36ab19e7c0e280e97ffb","abstract_canon_sha256":"45918be90a912b8c24e3434159fbf8b6dc712f66a1d78214225bf8bb6789fe60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:10.194527Z","signature_b64":"hT+7gngVqD4nID43MXzzv72WAczKe/hyL6VBd4pWxL+UKNYXvRGaPtz4btMAi2yVrZbAtoFdaz2fS/bXwmHtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e913982671a37b979a01559a9a6f6d5ee9eb6baef18985f5b00acb03375f845b","last_reissued_at":"2026-05-18T00:06:10.193913Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:10.193913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games using Baselines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.GT","authors_text":"Marc Lanctot, Martin Schmid, Matej Moravcik, Michael Bowling, Neil Burch, Rudolf Kadlec","submitted_at":"2018-09-09T23:03:54Z","abstract_excerpt":"Learning strategies for imperfect information games from samples of interaction is a challenging problem. A common method for this setting, Monte Carlo Counterfactual Regret Minimization (MCCFR), can have slow long-term convergence rates due to high variance. In this paper, we introduce a variance reduction technique (VR-MCCFR) that applies to any sampling variant of MCCFR. Using this technique, per-iteration estimated values and updates are reformulated as a function of sampled values and state-action baselines, similar to their use in policy gradient reinforcement learning. The new formulati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03057","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":""},"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":"1809.03057","created_at":"2026-05-18T00:06:10.194011+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03057v1","created_at":"2026-05-18T00:06:10.194011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03057","created_at":"2026-05-18T00:06:10.194011+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EJZQJTRUN5Z","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EJZQJTRUN5ZPGQB","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EJZQJTR","created_at":"2026-05-18T12:32:08.215937+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/5EJZQJTRUN5ZPGQBKWNJU33NL3","json":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3.json","graph_json":"https://pith.science/api/pith-number/5EJZQJTRUN5ZPGQBKWNJU33NL3/graph.json","events_json":"https://pith.science/api/pith-number/5EJZQJTRUN5ZPGQBKWNJU33NL3/events.json","paper":"https://pith.science/paper/5EJZQJTR"},"agent_actions":{"view_html":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3","download_json":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3.json","view_paper":"https://pith.science/paper/5EJZQJTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03057&json=true","fetch_graph":"https://pith.science/api/pith-number/5EJZQJTRUN5ZPGQBKWNJU33NL3/graph.json","fetch_events":"https://pith.science/api/pith-number/5EJZQJTRUN5ZPGQBKWNJU33NL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3/action/storage_attestation","attest_author":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3/action/author_attestation","sign_citation":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3/action/citation_signature","submit_replication":"https://pith.science/pith/5EJZQJTRUN5ZPGQBKWNJU33NL3/action/replication_record"}},"created_at":"2026-05-18T00:06:10.194011+00:00","updated_at":"2026-05-18T00:06:10.194011+00:00"}