{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MSP75ZY4Z7UEDEV3XGSP74KC3B","short_pith_number":"pith:MSP75ZY4","schema_version":"1.0","canonical_sha256":"649ffee71ccfe84192bbb9a4fff142d84e1b940c5ba4b0b11e0de8454f1836a6","source":{"kind":"arxiv","id":"1912.11912","version":1},"attestation_state":"computed","paper":{"title":"Quasi-Newton Trust Region Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arvind Raghunathan, Devesh Jha, Diego Romeres","submitted_at":"2019-12-26T18:29:38Z","abstract_excerpt":"We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement learning tasks with continuous controls. The algorithm has achieved state-of-the-art performance when used in reinforcement learning across a wide range of tasks. However, the algorithm suffers from a number of drawbacks including: lack of stepsize selection criterion, and slow convergence. We investigate the use of a trust region method using dogleg step and a "},"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":"1912.11912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-26T18:29:38Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"0f9097da985d456a04df1d9ecbc7cf5851b6ade4a950095161df35478561af28","abstract_canon_sha256":"13e3e0976d6547ea96ed81bfe542f7cd464ad1769641a1ecc37b69a08ea8d030"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:31.061513Z","signature_b64":"G0XAusNc0PxjkKezUaouPFkYBbl3Lc4CJTggSRkqc7D33WkHsOP070xj2JURyRO/JpYkfqoKNv0qh5CJwBthDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"649ffee71ccfe84192bbb9a4fff142d84e1b940c5ba4b0b11e0de8454f1836a6","last_reissued_at":"2026-07-05T00:28:31.061111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:31.061111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quasi-Newton Trust Region Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arvind Raghunathan, Devesh Jha, Diego Romeres","submitted_at":"2019-12-26T18:29:38Z","abstract_excerpt":"We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement learning tasks with continuous controls. The algorithm has achieved state-of-the-art performance when used in reinforcement learning across a wide range of tasks. However, the algorithm suffers from a number of drawbacks including: lack of stepsize selection criterion, and slow convergence. We investigate the use of a trust region method using dogleg step and a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11912","kind":"arxiv","version":1},"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/1912.11912/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":"1912.11912","created_at":"2026-07-05T00:28:31.061175+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.11912v1","created_at":"2026-07-05T00:28:31.061175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11912","created_at":"2026-07-05T00:28:31.061175+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSP75ZY4Z7UE","created_at":"2026-07-05T00:28:31.061175+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSP75ZY4Z7UEDEV3","created_at":"2026-07-05T00:28:31.061175+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSP75ZY4","created_at":"2026-07-05T00:28:31.061175+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/MSP75ZY4Z7UEDEV3XGSP74KC3B","json":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B.json","graph_json":"https://pith.science/api/pith-number/MSP75ZY4Z7UEDEV3XGSP74KC3B/graph.json","events_json":"https://pith.science/api/pith-number/MSP75ZY4Z7UEDEV3XGSP74KC3B/events.json","paper":"https://pith.science/paper/MSP75ZY4"},"agent_actions":{"view_html":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B","download_json":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B.json","view_paper":"https://pith.science/paper/MSP75ZY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.11912&json=true","fetch_graph":"https://pith.science/api/pith-number/MSP75ZY4Z7UEDEV3XGSP74KC3B/graph.json","fetch_events":"https://pith.science/api/pith-number/MSP75ZY4Z7UEDEV3XGSP74KC3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/action/storage_attestation","attest_author":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/action/author_attestation","sign_citation":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/action/citation_signature","submit_replication":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/action/replication_record"}},"created_at":"2026-07-05T00:28:31.061175+00:00","updated_at":"2026-07-05T00:28:31.061175+00:00"}