{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3DNUS24C4KVAFYXW3K2WP67BR6","short_pith_number":"pith:3DNUS24C","schema_version":"1.0","canonical_sha256":"d8db496b82e2aa02e2f6dab567fbe18f8c3d7495fb1d0be188412d0136db8d5b","source":{"kind":"arxiv","id":"1909.02769","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lior Shani, Shie Mannor, Yonathan Efroni","submitted_at":"2019-09-06T08:43:38Z","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"},"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":"1909.02769","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-06T08:43:38Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"c28ad2142e18cdb3674b1eaa7c7fd27d8f08bb4f9de514dfc135fe96568890bf","abstract_canon_sha256":"b4711c6c159e6c769be12f07b07261774853366decf62953eb1787f9a057399d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:25:50.138300Z","signature_b64":"dTMrxV801r79eGurw7QZVzozEQ34zEXfSUAMbvDKyVmsEqb+8Qmki0DYFOx41dQJUPxz1QLyg8s3ulyiKkEOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8db496b82e2aa02e2f6dab567fbe18f8c3d7495fb1d0be188412d0136db8d5b","last_reissued_at":"2026-07-05T00:25:50.137794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:25:50.137794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lior Shani, Shie Mannor, Yonathan Efroni","submitted_at":"2019-09-06T08:43:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02769","kind":"arxiv","version":2},"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/1909.02769/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":"1909.02769","created_at":"2026-07-05T00:25:50.137858+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.02769v2","created_at":"2026-07-05T00:25:50.137858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02769","created_at":"2026-07-05T00:25:50.137858+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DNUS24C4KVA","created_at":"2026-07-05T00:25:50.137858+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DNUS24C4KVAFYXW","created_at":"2026-07-05T00:25:50.137858+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DNUS24C","created_at":"2026-07-05T00:25:50.137858+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/3DNUS24C4KVAFYXW3K2WP67BR6","json":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6.json","graph_json":"https://pith.science/api/pith-number/3DNUS24C4KVAFYXW3K2WP67BR6/graph.json","events_json":"https://pith.science/api/pith-number/3DNUS24C4KVAFYXW3K2WP67BR6/events.json","paper":"https://pith.science/paper/3DNUS24C"},"agent_actions":{"view_html":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6","download_json":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6.json","view_paper":"https://pith.science/paper/3DNUS24C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.02769&json=true","fetch_graph":"https://pith.science/api/pith-number/3DNUS24C4KVAFYXW3K2WP67BR6/graph.json","fetch_events":"https://pith.science/api/pith-number/3DNUS24C4KVAFYXW3K2WP67BR6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6/action/storage_attestation","attest_author":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6/action/author_attestation","sign_citation":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6/action/citation_signature","submit_replication":"https://pith.science/pith/3DNUS24C4KVAFYXW3K2WP67BR6/action/replication_record"}},"created_at":"2026-07-05T00:25:50.137858+00:00","updated_at":"2026-07-05T00:25:50.137858+00:00"}