{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:FF5XMJD355AUNZ7KI2TSBUBCCH","short_pith_number":"pith:FF5XMJD3","schema_version":"1.0","canonical_sha256":"297b76247bef4146e7ea46a720d02211cdd26e9fd82f3fa7feffd3f67206778b","source":{"kind":"arxiv","id":"1707.01891","version":3},"attestation_state":"computed","paper":{"title":"Trust-PCL: An Off-Policy Trust Region Method for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dale Schuurmans, Kelvin Xu, Mohammad Norouzi, Ofir Nachum","submitted_at":"2017-07-06T17:50:19Z","abstract_excerpt":"Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective for continuous control, they typically require a prohibitively large amount of on-policy interaction with the environment. To address this problem, we propose an off-policy trust region method, Trust-PCL. The algorithm is the result of observing that the optimal policy and state values of a maximum reward objective with a relative-entropy regularizer satisfy a set of multi-step pathwise consistencies along any path. T"},"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":"1707.01891","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-07-06T17:50:19Z","cross_cats_sorted":[],"title_canon_sha256":"c55c3a10a96058f085111d40108a8068bd97c7b92e666770e6b0ddb5d595ed25","abstract_canon_sha256":"b24aa58dc7165d68253be75e20c2dfdc827a34a31af76e3778f9348445f88b1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:44.653105Z","signature_b64":"W7gKAC/YA8BIgtAGn/72rZT3PeJOBwRf6JZCvcuw5S3iiUNKtv240VfqGQShM1P95kfF+07T/E/xyWCvjjaZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"297b76247bef4146e7ea46a720d02211cdd26e9fd82f3fa7feffd3f67206778b","last_reissued_at":"2026-05-18T00:22:44.652666Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:44.652666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trust-PCL: An Off-Policy Trust Region Method for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dale Schuurmans, Kelvin Xu, Mohammad Norouzi, Ofir Nachum","submitted_at":"2017-07-06T17:50:19Z","abstract_excerpt":"Trust region methods, such as TRPO, are often used to stabilize policy optimization algorithms in reinforcement learning (RL). While current trust region strategies are effective for continuous control, they typically require a prohibitively large amount of on-policy interaction with the environment. To address this problem, we propose an off-policy trust region method, Trust-PCL. The algorithm is the result of observing that the optimal policy and state values of a maximum reward objective with a relative-entropy regularizer satisfy a set of multi-step pathwise consistencies along any path. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.01891","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1707.01891","created_at":"2026-05-18T00:22:44.652731+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.01891v3","created_at":"2026-05-18T00:22:44.652731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.01891","created_at":"2026-05-18T00:22:44.652731+00:00"},{"alias_kind":"pith_short_12","alias_value":"FF5XMJD355AU","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FF5XMJD355AUNZ7K","created_at":"2026-05-18T12:31:15.632608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FF5XMJD3","created_at":"2026-05-18T12:31:15.632608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1805.00909","citing_title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"1911.11361","citing_title":"Behavior Regularized Offline Reinforcement Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"1812.05905","citing_title":"Soft Actor-Critic Algorithms and Applications","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"1801.01290","citing_title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH","json":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH.json","graph_json":"https://pith.science/api/pith-number/FF5XMJD355AUNZ7KI2TSBUBCCH/graph.json","events_json":"https://pith.science/api/pith-number/FF5XMJD355AUNZ7KI2TSBUBCCH/events.json","paper":"https://pith.science/paper/FF5XMJD3"},"agent_actions":{"view_html":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH","download_json":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH.json","view_paper":"https://pith.science/paper/FF5XMJD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.01891&json=true","fetch_graph":"https://pith.science/api/pith-number/FF5XMJD355AUNZ7KI2TSBUBCCH/graph.json","fetch_events":"https://pith.science/api/pith-number/FF5XMJD355AUNZ7KI2TSBUBCCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH/action/storage_attestation","attest_author":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH/action/author_attestation","sign_citation":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH/action/citation_signature","submit_replication":"https://pith.science/pith/FF5XMJD355AUNZ7KI2TSBUBCCH/action/replication_record"}},"created_at":"2026-05-18T00:22:44.652731+00:00","updated_at":"2026-05-18T00:22:44.652731+00:00"}