{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KHVLWZ7X56XLH2IWI4WBAU6MMX","short_pith_number":"pith:KHVLWZ7X","schema_version":"1.0","canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","source":{"kind":"arxiv","id":"1805.10755","version":2},"attestation_state":"computed","paper":{"title":"Dual Policy Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","submitted_at":"2018-05-28T03:41:56Z","abstract_excerpt":"Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated impressive practical performance (e.g., ExIt from [2], AlphaGo-Zero from [27]). This new family of algorithms maintains, and alternately optimizes, two policies: a fast, reactive policy (e.g., a deep neural network) deployed at test time, and a slow, non-reactive policy (e.g., Tree Search), that can plan multiple steps ahead. The reactive policy is updated under supervision from the non-reactive policy, while the non-reactive policy is improved with guidance from the reactive policy. In this work we stud"},"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":"1805.10755","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ad6c9fdf065b3888ea8bfc0c80a3141dd3e83eeaa7cf3ac6e16caacbd375e8d5","abstract_canon_sha256":"a487b32876e68df0ac09c8c47e3f96b8c58b57d150691678ce56e9d8fc462734"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:17.631793Z","signature_b64":"EJlSKHvP6+rSXEIOI6jGtYFaPSju1Rjb+QM+FHGsU+xWooyegzGWThl++ZsF7LnA3WZaGB+F/hyc9PQc1DVKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","last_reissued_at":"2026-05-17T23:49:17.631285Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:17.631285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Policy Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","submitted_at":"2018-05-28T03:41:56Z","abstract_excerpt":"Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated impressive practical performance (e.g., ExIt from [2], AlphaGo-Zero from [27]). This new family of algorithms maintains, and alternately optimizes, two policies: a fast, reactive policy (e.g., a deep neural network) deployed at test time, and a slow, non-reactive policy (e.g., Tree Search), that can plan multiple steps ahead. The reactive policy is updated under supervision from the non-reactive policy, while the non-reactive policy is improved with guidance from the reactive policy. In this work we stud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10755","kind":"arxiv","version":2},"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":"1805.10755","created_at":"2026-05-17T23:49:17.631377+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10755v2","created_at":"2026-05-17T23:49:17.631377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10755","created_at":"2026-05-17T23:49:17.631377+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHVLWZ7X56XL","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHVLWZ7X56XLH2IW","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHVLWZ7X","created_at":"2026-05-18T12:32:33.847187+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/KHVLWZ7X56XLH2IWI4WBAU6MMX","json":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX.json","graph_json":"https://pith.science/api/pith-number/KHVLWZ7X56XLH2IWI4WBAU6MMX/graph.json","events_json":"https://pith.science/api/pith-number/KHVLWZ7X56XLH2IWI4WBAU6MMX/events.json","paper":"https://pith.science/paper/KHVLWZ7X"},"agent_actions":{"view_html":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX","download_json":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX.json","view_paper":"https://pith.science/paper/KHVLWZ7X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10755&json=true","fetch_graph":"https://pith.science/api/pith-number/KHVLWZ7X56XLH2IWI4WBAU6MMX/graph.json","fetch_events":"https://pith.science/api/pith-number/KHVLWZ7X56XLH2IWI4WBAU6MMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/action/storage_attestation","attest_author":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/action/author_attestation","sign_citation":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/action/citation_signature","submit_replication":"https://pith.science/pith/KHVLWZ7X56XLH2IWI4WBAU6MMX/action/replication_record"}},"created_at":"2026-05-17T23:49:17.631377+00:00","updated_at":"2026-05-17T23:49:17.631377+00:00"}