{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:4RABHY6PEZSTXLAJG7BVVB6ZHF","short_pith_number":"pith:4RABHY6P","schema_version":"1.0","canonical_sha256":"e44013e3cf26653bac0937c35a87d9396a23d8f6574ca5f5cbc58d9e0ffd9043","source":{"kind":"arxiv","id":"1708.05144","version":2},"attestation_state":"computed","paper":{"title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elman Mansimov, Jimmy Ba, Roger Grosse, Shun Liao, Yuhuai Wu","submitted_at":"2017-08-17T06:14:48Z","abstract_excerpt":"In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to optimize both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region; hence we call our method Actor Critic using Kronecker-Factored Trust Region (ACKTR). To the best of our knowledge, this is the first scalable trust region natural gradient method for actor-critic methods. It is also a method that learns non-trivial task"},"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":"1708.05144","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-17T06:14:48Z","cross_cats_sorted":[],"title_canon_sha256":"cf84b3cc746fb4aece830ed446435740ca16287250318e453dc64ef5877cd7cd","abstract_canon_sha256":"dd313e5c3a51b22d31802072a9c22dd72af8c6baa98f4303705ccab5ba9588d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:50.218502Z","signature_b64":"oChladpQH6q2dE+Tx5k64ZarvpLqgGckp7nJjPo20LGG1meIbQalTuZAq3xWa62o957wLtMmla/yzmSBJsc7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e44013e3cf26653bac0937c35a87d9396a23d8f6574ca5f5cbc58d9e0ffd9043","last_reissued_at":"2026-05-18T00:37:50.217876Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:50.217876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Elman Mansimov, Jimmy Ba, Roger Grosse, Shun Liao, Yuhuai Wu","submitted_at":"2017-08-17T06:14:48Z","abstract_excerpt":"In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to optimize both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region; hence we call our method Actor Critic using Kronecker-Factored Trust Region (ACKTR). To the best of our knowledge, this is the first scalable trust region natural gradient method for actor-critic methods. It is also a method that learns non-trivial task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05144","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":""},"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":"1708.05144","created_at":"2026-05-18T00:37:50.217962+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.05144v2","created_at":"2026-05-18T00:37:50.217962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05144","created_at":"2026-05-18T00:37:50.217962+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RABHY6PEZST","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RABHY6PEZSTXLAJ","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RABHY6P","created_at":"2026-05-18T12:31:00.734936+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/4RABHY6PEZSTXLAJG7BVVB6ZHF","json":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF.json","graph_json":"https://pith.science/api/pith-number/4RABHY6PEZSTXLAJG7BVVB6ZHF/graph.json","events_json":"https://pith.science/api/pith-number/4RABHY6PEZSTXLAJG7BVVB6ZHF/events.json","paper":"https://pith.science/paper/4RABHY6P"},"agent_actions":{"view_html":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF","download_json":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF.json","view_paper":"https://pith.science/paper/4RABHY6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.05144&json=true","fetch_graph":"https://pith.science/api/pith-number/4RABHY6PEZSTXLAJG7BVVB6ZHF/graph.json","fetch_events":"https://pith.science/api/pith-number/4RABHY6PEZSTXLAJG7BVVB6ZHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/action/storage_attestation","attest_author":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/action/author_attestation","sign_citation":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/action/citation_signature","submit_replication":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/action/replication_record"}},"created_at":"2026-05-18T00:37:50.217962+00:00","updated_at":"2026-05-18T00:37:50.217962+00:00"}