{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:KHVLWZ7X56XLH2IWI4WBAU6MMX","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":"a487b32876e68df0ac09c8c47e3f96b8c58b57d150691678ce56e9d8fc462734","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","title_canon_sha256":"ad6c9fdf065b3888ea8bfc0c80a3141dd3e83eeaa7cf3ac6e16caacbd375e8d5"},"schema_version":"1.0","source":{"id":"1805.10755","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10755","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10755v2","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10755","created_at":"2026-05-17T23:49:17Z"},{"alias_kind":"pith_short_12","alias_value":"KHVLWZ7X56XL","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"KHVLWZ7X56XLH2IW","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"KHVLWZ7X","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:5fdd50c2ed33315e428470a116e64daa93650e9d69910d9956625fee371fb5dc","target":"graph","created_at":"2026-05-17T23:49:17Z","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":"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","authors_text":"Byron Boots, Geoffrey J. Gordon, J. Andrew Bagnell, Wen Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","title":"Dual Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10755","kind":"arxiv","version":2},"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":"sha256:87c2924e197c15032be8b0b02587fdd45af338e1a77bbdd85aa0668522687791","target":"record","created_at":"2026-05-17T23:49:17Z","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":"a487b32876e68df0ac09c8c47e3f96b8c58b57d150691678ce56e9d8fc462734","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T03:41:56Z","title_canon_sha256":"ad6c9fdf065b3888ea8bfc0c80a3141dd3e83eeaa7cf3ac6e16caacbd375e8d5"},"schema_version":"1.0","source":{"id":"1805.10755","kind":"arxiv","version":2}},"canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51eabb67f7efaeb3e916472c1053cc65ea009a045f02e3a880251564850fd522","first_computed_at":"2026-05-17T23:49:17.631285Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:17.631285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EJlSKHvP6+rSXEIOI6jGtYFaPSju1Rjb+QM+FHGsU+xWooyegzGWThl++ZsF7LnA3WZaGB+F/hyc9PQc1DVKCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:17.631793Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10755","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87c2924e197c15032be8b0b02587fdd45af338e1a77bbdd85aa0668522687791","sha256:5fdd50c2ed33315e428470a116e64daa93650e9d69910d9956625fee371fb5dc"],"state_sha256":"6a31724d89daa1adad4d2a76bd96a0256c8cdef7ad749af6c798906b48af3bf5"}