{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3DNUS24C4KVAFYXW3K2WP67BR6","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":"b4711c6c159e6c769be12f07b07261774853366decf62953eb1787f9a057399d","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-06T08:43:38Z","title_canon_sha256":"c28ad2142e18cdb3674b1eaa7c7fd27d8f08bb4f9de514dfc135fe96568890bf"},"schema_version":"1.0","source":{"id":"1909.02769","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02769","created_at":"2026-07-05T00:25:50Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02769v2","created_at":"2026-07-05T00:25:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02769","created_at":"2026-07-05T00:25:50Z"},{"alias_kind":"pith_short_12","alias_value":"3DNUS24C4KVA","created_at":"2026-07-05T00:25:50Z"},{"alias_kind":"pith_short_16","alias_value":"3DNUS24C4KVAFYXW","created_at":"2026-07-05T00:25:50Z"},{"alias_kind":"pith_short_8","alias_value":"3DNUS24C","created_at":"2026-07-05T00:25:50Z"}],"graph_snapshots":[{"event_id":"sha256:8468f5ba71f50a5f59d6f30d9069e2242f9245920d09e43aa9a116b68a23d115","target":"graph","created_at":"2026-07-05T00:25:50Z","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/1909.02769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be 'close' to one another, is iteratively solved. Nevertheless, TRPO has been considered a heuristic algorithm inspired by Conservative Policy Iteration (CPI). We show that the adaptive scaling mechanism used in TRPO is in fact the natural \"RL version\" of traditional trust-region methods from convex analysis. We first analyze TRPO in the planning setting, in which we have access to the model a","authors_text":"Lior Shani, Shie Mannor, Yonathan Efroni","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-06T08:43:38Z","title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02769","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":"sha256:07f4d569788f64e6796205d409218c66d306663247f723d3bb24a92041ec7502","target":"record","created_at":"2026-07-05T00:25:50Z","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":"b4711c6c159e6c769be12f07b07261774853366decf62953eb1787f9a057399d","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-06T08:43:38Z","title_canon_sha256":"c28ad2142e18cdb3674b1eaa7c7fd27d8f08bb4f9de514dfc135fe96568890bf"},"schema_version":"1.0","source":{"id":"1909.02769","kind":"arxiv","version":2}},"canonical_sha256":"d8db496b82e2aa02e2f6dab567fbe18f8c3d7495fb1d0be188412d0136db8d5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8db496b82e2aa02e2f6dab567fbe18f8c3d7495fb1d0be188412d0136db8d5b","first_computed_at":"2026-07-05T00:25:50.137794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:25:50.137794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dTMrxV801r79eGurw7QZVzozEQ34zEXfSUAMbvDKyVmsEqb+8Qmki0DYFOx41dQJUPxz1QLyg8s3ulyiKkEOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:25:50.138300Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02769","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07f4d569788f64e6796205d409218c66d306663247f723d3bb24a92041ec7502","sha256:8468f5ba71f50a5f59d6f30d9069e2242f9245920d09e43aa9a116b68a23d115"],"state_sha256":"9b25abc7754b90b4b14dd7be8c383e74f3ecb0b77ba430640c0b7dc6b1102ce1"}