{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5EJZQJTRUN5ZPGQBKWNJU33NL3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"45918be90a912b8c24e3434159fbf8b6dc712f66a1d78214225bf8bb6789fe60","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2018-09-09T23:03:54Z","title_canon_sha256":"8870f4b1f63058bb1123a43685d3dc79f0631e4c6add36ab19e7c0e280e97ffb"},"schema_version":"1.0","source":{"id":"1809.03057","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.03057","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"1809.03057v1","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03057","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"5EJZQJTRUN5Z","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5EJZQJTRUN5ZPGQB","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5EJZQJTR","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:be3288f6936c884a2ba13039cb6578f6c843044bf1ba64ddd8f377de08420829","target":"graph","created_at":"2026-05-18T00:06:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Marc Lanctot, Martin Schmid, Matej Moravcik, Michael Bowling, Neil Burch, Rudolf Kadlec","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2018-09-09T23:03:54Z","title":"Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VR-MCCFR) for Extensive Form Games using Baselines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03057","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e7d4fe851cbc163c40cee55d5750367951ac9efc4a0acea226680ca27ce410ed","target":"record","created_at":"2026-05-18T00:06:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"45918be90a912b8c24e3434159fbf8b6dc712f66a1d78214225bf8bb6789fe60","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2018-09-09T23:03:54Z","title_canon_sha256":"8870f4b1f63058bb1123a43685d3dc79f0631e4c6add36ab19e7c0e280e97ffb"},"schema_version":"1.0","source":{"id":"1809.03057","kind":"arxiv","version":1}},"canonical_sha256":"e913982671a37b979a01559a9a6f6d5ee9eb6baef18985f5b00acb03375f845b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e913982671a37b979a01559a9a6f6d5ee9eb6baef18985f5b00acb03375f845b","first_computed_at":"2026-05-18T00:06:10.193913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:10.193913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hT+7gngVqD4nID43MXzzv72WAczKe/hyL6VBd4pWxL+UKNYXvRGaPtz4btMAi2yVrZbAtoFdaz2fS/bXwmHtDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:10.194527Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.03057","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7d4fe851cbc163c40cee55d5750367951ac9efc4a0acea226680ca27ce410ed","sha256:be3288f6936c884a2ba13039cb6578f6c843044bf1ba64ddd8f377de08420829"],"state_sha256":"0eaba60541ae95276503f451088d764cd107c1f0d0b6755943839a0ff1d38192"}