{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:YKWFHUU6LKUAWRWBBOVCLY3BXA","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":"1581b0fd2e7c4395f97ff92062bcbd3012196c00ba6ddc6294471cad58a64a34","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:49:23Z","title_canon_sha256":"55764730d29344e6a712044a2e67a8fb6e718840d37b35e806b049e4c2cd6bb3"},"schema_version":"1.0","source":{"id":"2006.06600","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06600","created_at":"2026-07-05T02:54:50Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06600v2","created_at":"2026-07-05T02:54:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06600","created_at":"2026-07-05T02:54:50Z"},{"alias_kind":"pith_short_12","alias_value":"YKWFHUU6LKUA","created_at":"2026-07-05T02:54:50Z"},{"alias_kind":"pith_short_16","alias_value":"YKWFHUU6LKUAWRWB","created_at":"2026-07-05T02:54:50Z"},{"alias_kind":"pith_short_8","alias_value":"YKWFHUU6","created_at":"2026-07-05T02:54:50Z"}],"graph_snapshots":[{"event_id":"sha256:47d45860e67bd085d0823b03385490201dc7fdfa3db0c7e6fa9729de688718c1","target":"graph","created_at":"2026-07-05T02:54:50Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.06600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient (PG) algorithms have been widely used in reinforcement learning (RL). However, PG algorithms rely on exploiting the value function being learned with the first-order update locally, which results in limited sample efficiency. In this work, we propose an alternative method called Zeroth-Order Supervised Policy Improvement (ZOSPI). ZOSPI exploits the estimated value function $Q$ globally while preserving the local exploitation of the PG methods based on zeroth-order policy optimization. This learning paradigm follows Q-learning but overcomes the difficulty of efficiently operatin","authors_text":"Bo Dai, Bolei Zhou, Hao Sun, Jiechao Xiong, Meng Fang, Yuhang Song, Ziping Xu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:49:23Z","title":"Zeroth-Order Supervised Policy Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06600","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":"sha256:560e6591a9418b9a98bf7ba4992d16ac031e8b9b6ebe156198e77017f6e74315","target":"record","created_at":"2026-07-05T02:54:50Z","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":"1581b0fd2e7c4395f97ff92062bcbd3012196c00ba6ddc6294471cad58a64a34","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-11T16:49:23Z","title_canon_sha256":"55764730d29344e6a712044a2e67a8fb6e718840d37b35e806b049e4c2cd6bb3"},"schema_version":"1.0","source":{"id":"2006.06600","kind":"arxiv","version":2}},"canonical_sha256":"c2ac53d29e5aa80b46c10baa25e361b82996dd6edfb58f01dfe92e063e4878ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2ac53d29e5aa80b46c10baa25e361b82996dd6edfb58f01dfe92e063e4878ae","first_computed_at":"2026-07-05T02:54:50.350430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:50.350430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MangCtqwVD0pgQO4O+O0bIHLrJIZ5hF890t0vHij5s2OtAPzOj69WP1zBXlyYrR8HkNjzxtEpNWPegm3AyKdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:50.350910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06600","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:560e6591a9418b9a98bf7ba4992d16ac031e8b9b6ebe156198e77017f6e74315","sha256:47d45860e67bd085d0823b03385490201dc7fdfa3db0c7e6fa9729de688718c1"],"state_sha256":"929977aaa44302a2888ef126a821161fe33dfc063d9a208a646419fd1e695305"}