{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TQWC4OVS5ALWIBXKLZS5WZRII5","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":"6c7ad868a4961c2cc3cb34c593c15a502659fd92d3c2e99c7836809b5c8e113a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T13:00:21Z","title_canon_sha256":"e41057f8288c2535868c13049d263d7ac7cc3322ebbeded0a941b63a461daeb7"},"schema_version":"1.0","source":{"id":"1904.03646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03646","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03646v1","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03646","created_at":"2026-05-17T23:49:12Z"},{"alias_kind":"pith_short_12","alias_value":"TQWC4OVS5ALW","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TQWC4OVS5ALWIBXK","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TQWC4OVS","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:21f8bcd1ad59c087fcd5265ecd127dea2a81c98f9725a9ef497299fab18ca57c","target":"graph","created_at":"2026-05-17T23:49:12Z","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":"Monte Carlo Tree Search (MCTS) algorithms perform simulation-based search to improve policies online. During search, the simulation policy is adapted to explore the most promising lines of play. MCTS has been used by state-of-the-art programs for many problems, however a disadvantage to MCTS is that it estimates the values of states with Monte Carlo averages, stored in a search tree; this does not scale to games with very high branching factors. We propose an alternative simulation-based search method, Policy Gradient Search (PGS), which adapts a neural network simulation policy online via pol","authors_text":"John Schulman, Philipp Moritz, Robert Nishihara, Thomas Anthony, Tim Salimans","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T13:00:21Z","title":"Policy Gradient Search: Online Planning and Expert Iteration without Search Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03646","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":"sha256:01c993e2ed7cdb50c0eb4d3e918de689010149e386ac16cf0d838a4d84611d0a","target":"record","created_at":"2026-05-17T23:49:12Z","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":"6c7ad868a4961c2cc3cb34c593c15a502659fd92d3c2e99c7836809b5c8e113a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T13:00:21Z","title_canon_sha256":"e41057f8288c2535868c13049d263d7ac7cc3322ebbeded0a941b63a461daeb7"},"schema_version":"1.0","source":{"id":"1904.03646","kind":"arxiv","version":1}},"canonical_sha256":"9c2c2e3ab2e8176406ea5e65db66284759f7e93890d02ad691ade6d7e36965e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c2c2e3ab2e8176406ea5e65db66284759f7e93890d02ad691ade6d7e36965e3","first_computed_at":"2026-05-17T23:49:12.648840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:12.648840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oZ11VURHLu2+Oai83/xfGAduRIxE7v04UkcN17oeNetcaS/Es8XZ+ynBg97SCRbM2ERnbU0e0GaWPw3QhlsoBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:12.649517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01c993e2ed7cdb50c0eb4d3e918de689010149e386ac16cf0d838a4d84611d0a","sha256:21f8bcd1ad59c087fcd5265ecd127dea2a81c98f9725a9ef497299fab18ca57c"],"state_sha256":"79ad99c1e02536bf8dae27e332f2246d2c2b919b61fe7720442c319038bcd20e"}