{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4MOANNBJCJF5D5IAKB2X7IAFZ2","short_pith_number":"pith:4MOANNBJ","schema_version":"1.0","canonical_sha256":"e31c06b429124bd1f50050757fa005ceb5fb5ac378439e927dffaa1edee83b4d","source":{"kind":"arxiv","id":"1912.05830","version":4},"attestation_state":"computed","paper":{"title":"Provably Efficient Exploration in Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Qi Cai, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-12-12T08:40:02Z","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"},"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":"1912.05830","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-12T08:40:02Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"306bfa8e238531991a59823741bed0f2b9b642e041232bc3a3130a12b2172f41","abstract_canon_sha256":"33043b505c37b065bfa43f0b4d844ee442cf4df8cfbc10aaa0714f489d8e3f79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:39.846661Z","signature_b64":"0wnurT3mXC8CX5OkV3r5cEDZ2kNYQa06bHzhBfJjxDjlhxumlb2Lp5Z+u7SU6m0qEebYAdqXy5mX6MDBlVEDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e31c06b429124bd1f50050757fa005ceb5fb5ac378439e927dffaa1edee83b4d","last_reissued_at":"2026-07-05T08:02:39.846267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:39.846267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Exploration in Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chi Jin, Qi Cai, Zhaoran Wang, Zhuoran Yang","submitted_at":"2019-12-12T08:40:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05830","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.05830/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1912.05830","created_at":"2026-07-05T08:02:39.846334+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.05830v4","created_at":"2026-07-05T08:02:39.846334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05830","created_at":"2026-07-05T08:02:39.846334+00:00"},{"alias_kind":"pith_short_12","alias_value":"4MOANNBJCJF5","created_at":"2026-07-05T08:02:39.846334+00:00"},{"alias_kind":"pith_short_16","alias_value":"4MOANNBJCJF5D5IA","created_at":"2026-07-05T08:02:39.846334+00:00"},{"alias_kind":"pith_short_8","alias_value":"4MOANNBJ","created_at":"2026-07-05T08:02:39.846334+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/4MOANNBJCJF5D5IAKB2X7IAFZ2","json":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2.json","graph_json":"https://pith.science/api/pith-number/4MOANNBJCJF5D5IAKB2X7IAFZ2/graph.json","events_json":"https://pith.science/api/pith-number/4MOANNBJCJF5D5IAKB2X7IAFZ2/events.json","paper":"https://pith.science/paper/4MOANNBJ"},"agent_actions":{"view_html":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2","download_json":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2.json","view_paper":"https://pith.science/paper/4MOANNBJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.05830&json=true","fetch_graph":"https://pith.science/api/pith-number/4MOANNBJCJF5D5IAKB2X7IAFZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/4MOANNBJCJF5D5IAKB2X7IAFZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2/action/storage_attestation","attest_author":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2/action/author_attestation","sign_citation":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2/action/citation_signature","submit_replication":"https://pith.science/pith/4MOANNBJCJF5D5IAKB2X7IAFZ2/action/replication_record"}},"created_at":"2026-07-05T08:02:39.846334+00:00","updated_at":"2026-07-05T08:02:39.846334+00:00"}