{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4MOANNBJCJF5D5IAKB2X7IAFZ2","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":"33043b505c37b065bfa43f0b4d844ee442cf4df8cfbc10aaa0714f489d8e3f79","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T08:40:02Z","title_canon_sha256":"306bfa8e238531991a59823741bed0f2b9b642e041232bc3a3130a12b2172f41"},"schema_version":"1.0","source":{"id":"1912.05830","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05830","created_at":"2026-07-05T08:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05830v4","created_at":"2026-07-05T08:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05830","created_at":"2026-07-05T08:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"4MOANNBJCJF5","created_at":"2026-07-05T08:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"4MOANNBJCJF5D5IA","created_at":"2026-07-05T08:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"4MOANNBJ","created_at":"2026-07-05T08:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:246c4a9a0c9400fe0830e22c487afd0b374345c7ae6d16d528a161b7ef259216","target":"graph","created_at":"2026-07-05T08:02:39Z","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/1912.05830/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While policy-based reinforcement learning (RL) achieves tremendous successes in practice, it is significantly less understood in theory, especially compared with value-based RL. In particular, it remains elusive how to design a provably efficient policy optimization algorithm that incorporates exploration. To bridge such a gap, this paper proposes an Optimistic variant of the Proximal Policy Optimization algorithm (OPPO), which follows an ``optimistic version'' of the policy gradient direction. This paper proves that, in the problem of episodic Markov decision process with linear function appr","authors_text":"Chi Jin, Qi Cai, Zhaoran Wang, Zhuoran Yang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T08:40:02Z","title":"Provably Efficient Exploration in Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05830","kind":"arxiv","version":4},"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":"sha256:64cf9df828bb0af45550b5a2d29c7917f3ad2ea3fafe075e14885ec8d85433be","target":"record","created_at":"2026-07-05T08:02:39Z","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":"33043b505c37b065bfa43f0b4d844ee442cf4df8cfbc10aaa0714f489d8e3f79","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T08:40:02Z","title_canon_sha256":"306bfa8e238531991a59823741bed0f2b9b642e041232bc3a3130a12b2172f41"},"schema_version":"1.0","source":{"id":"1912.05830","kind":"arxiv","version":4}},"canonical_sha256":"e31c06b429124bd1f50050757fa005ceb5fb5ac378439e927dffaa1edee83b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e31c06b429124bd1f50050757fa005ceb5fb5ac378439e927dffaa1edee83b4d","first_computed_at":"2026-07-05T08:02:39.846267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:39.846267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0wnurT3mXC8CX5OkV3r5cEDZ2kNYQa06bHzhBfJjxDjlhxumlb2Lp5Z+u7SU6m0qEebYAdqXy5mX6MDBlVEDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:39.846661Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05830","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64cf9df828bb0af45550b5a2d29c7917f3ad2ea3fafe075e14885ec8d85433be","sha256:246c4a9a0c9400fe0830e22c487afd0b374345c7ae6d16d528a161b7ef259216"],"state_sha256":"882426abd1b7d77c26528b8dd12d3ec46842cb10a99f95295fa63deb4f3f487d"}