{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MSP75ZY4Z7UEDEV3XGSP74KC3B","short_pith_number":"pith:MSP75ZY4","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"},"canonical_sha256":"649ffee71ccfe84192bbb9a4fff142d84e1b940c5ba4b0b11e0de8454f1836a6","source":{"kind":"arxiv","id":"1912.11912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.11912","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"1912.11912v1","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11912","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"MSP75ZY4Z7UE","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"MSP75ZY4Z7UEDEV3","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"MSP75ZY4","created_at":"2026-07-05T00:28:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MSP75ZY4Z7UEDEV3XGSP74KC3B","target":"record","payload":{"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"},"canonical_sha256":"649ffee71ccfe84192bbb9a4fff142d84e1b940c5ba4b0b11e0de8454f1836a6","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"},"source_kind":"arxiv","source_id":"1912.11912","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3KeOcV2La0fmniCk/bgqvENUD47U+d9rPK+uRGLy2B++gjus+mNw6hWanZ3VeTAY/DKbKt9xCIRFVSM771mPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:54:49.595948Z"},"content_sha256":"dbe6e2c4cc0c8365bbc1cebae42b265d13646f9aad9b3daf2c205d5b9eab22bb","schema_version":"1.0","event_id":"sha256:dbe6e2c4cc0c8365bbc1cebae42b265d13646f9aad9b3daf2c205d5b9eab22bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MSP75ZY4Z7UEDEV3XGSP74KC3B","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:28:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gs5Qdu3p7TMw21Kvjv9hIWyPp9vb3HLsbTzp+lDpaBCeZrSNjqZhf5G7uqjMGEvZ0WGbjDgYQNuF03SjK7ZbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:54:49.596329Z"},"content_sha256":"570725e1fb37a018f33ddc3ff3d96843d945483bbf2e03c42aef6736fd8c925d","schema_version":"1.0","event_id":"sha256:570725e1fb37a018f33ddc3ff3d96843d945483bbf2e03c42aef6736fd8c925d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/bundle.json","state_url":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T23:54:49Z","links":{"resolver":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B","bundle":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/bundle.json","state":"https://pith.science/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSP75ZY4Z7UEDEV3XGSP74KC3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MSP75ZY4Z7UEDEV3XGSP74KC3B","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":"13e3e0976d6547ea96ed81bfe542f7cd464ad1769641a1ecc37b69a08ea8d030","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-26T18:29:38Z","title_canon_sha256":"0f9097da985d456a04df1d9ecbc7cf5851b6ade4a950095161df35478561af28"},"schema_version":"1.0","source":{"id":"1912.11912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.11912","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"1912.11912v1","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.11912","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"MSP75ZY4Z7UE","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"MSP75ZY4Z7UEDEV3","created_at":"2026-07-05T00:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"MSP75ZY4","created_at":"2026-07-05T00:28:31Z"}],"graph_snapshots":[{"event_id":"sha256:570725e1fb37a018f33ddc3ff3d96843d945483bbf2e03c42aef6736fd8c925d","target":"graph","created_at":"2026-07-05T00:28:31Z","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/1912.11912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Arvind Raghunathan, Devesh Jha, Diego Romeres","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-26T18:29:38Z","title":"Quasi-Newton Trust Region Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.11912","kind":"arxiv","version":1},"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:dbe6e2c4cc0c8365bbc1cebae42b265d13646f9aad9b3daf2c205d5b9eab22bb","target":"record","created_at":"2026-07-05T00:28:31Z","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":"13e3e0976d6547ea96ed81bfe542f7cd464ad1769641a1ecc37b69a08ea8d030","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-26T18:29:38Z","title_canon_sha256":"0f9097da985d456a04df1d9ecbc7cf5851b6ade4a950095161df35478561af28"},"schema_version":"1.0","source":{"id":"1912.11912","kind":"arxiv","version":1}},"canonical_sha256":"649ffee71ccfe84192bbb9a4fff142d84e1b940c5ba4b0b11e0de8454f1836a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"649ffee71ccfe84192bbb9a4fff142d84e1b940c5ba4b0b11e0de8454f1836a6","first_computed_at":"2026-07-05T00:28:31.061111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:31.061111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G0XAusNc0PxjkKezUaouPFkYBbl3Lc4CJTggSRkqc7D33WkHsOP070xj2JURyRO/JpYkfqoKNv0qh5CJwBthDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:31.061513Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.11912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbe6e2c4cc0c8365bbc1cebae42b265d13646f9aad9b3daf2c205d5b9eab22bb","sha256:570725e1fb37a018f33ddc3ff3d96843d945483bbf2e03c42aef6736fd8c925d"],"state_sha256":"47c38fd2f7b5fb158918851d06e3672a076a943845fd2700401302a49dfe2a07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g9gVvIZGy+cj7RRSe1AKp+7kghzUF9OZGJGrqKKdOHZKMp1/rCvdwNZp+1mGfSeyijgmnQj04zXRICIhE/gaBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:54:49.599579Z","bundle_sha256":"b83533048b726810d9ab34209f9aff29e8025a2b5c1dd8150ccd7b1b5cbca257"}}