{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TQWC4OVS5ALWIBXKLZS5WZRII5","short_pith_number":"pith:TQWC4OVS","schema_version":"1.0","canonical_sha256":"9c2c2e3ab2e8176406ea5e65db66284759f7e93890d02ad691ade6d7e36965e3","source":{"kind":"arxiv","id":"1904.03646","version":1},"attestation_state":"computed","paper":{"title":"Policy Gradient Search: Online Planning and Expert Iteration without Search Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"John Schulman, Philipp Moritz, Robert Nishihara, Thomas Anthony, Tim Salimans","submitted_at":"2019-04-07T13:00:21Z","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"},"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":"1904.03646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T13:00:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e41057f8288c2535868c13049d263d7ac7cc3322ebbeded0a941b63a461daeb7","abstract_canon_sha256":"6c7ad868a4961c2cc3cb34c593c15a502659fd92d3c2e99c7836809b5c8e113a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:12.649517Z","signature_b64":"oZ11VURHLu2+Oai83/xfGAduRIxE7v04UkcN17oeNetcaS/Es8XZ+ynBg97SCRbM2ERnbU0e0GaWPw3QhlsoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c2c2e3ab2e8176406ea5e65db66284759f7e93890d02ad691ade6d7e36965e3","last_reissued_at":"2026-05-17T23:49:12.648840Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:12.648840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient Search: Online Planning and Expert Iteration without Search Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"John Schulman, Philipp Moritz, Robert Nishihara, Thomas Anthony, Tim Salimans","submitted_at":"2019-04-07T13:00:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03646","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":"1904.03646","created_at":"2026-05-17T23:49:12.648948+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03646v1","created_at":"2026-05-17T23:49:12.648948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03646","created_at":"2026-05-17T23:49:12.648948+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQWC4OVS5ALW","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQWC4OVS5ALWIBXK","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQWC4OVS","created_at":"2026-05-18T12:33:30.264802+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/TQWC4OVS5ALWIBXKLZS5WZRII5","json":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5.json","graph_json":"https://pith.science/api/pith-number/TQWC4OVS5ALWIBXKLZS5WZRII5/graph.json","events_json":"https://pith.science/api/pith-number/TQWC4OVS5ALWIBXKLZS5WZRII5/events.json","paper":"https://pith.science/paper/TQWC4OVS"},"agent_actions":{"view_html":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5","download_json":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5.json","view_paper":"https://pith.science/paper/TQWC4OVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03646&json=true","fetch_graph":"https://pith.science/api/pith-number/TQWC4OVS5ALWIBXKLZS5WZRII5/graph.json","fetch_events":"https://pith.science/api/pith-number/TQWC4OVS5ALWIBXKLZS5WZRII5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5/action/storage_attestation","attest_author":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5/action/author_attestation","sign_citation":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5/action/citation_signature","submit_replication":"https://pith.science/pith/TQWC4OVS5ALWIBXKLZS5WZRII5/action/replication_record"}},"created_at":"2026-05-17T23:49:12.648948+00:00","updated_at":"2026-05-17T23:49:12.648948+00:00"}