{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4RABHY6PEZSTXLAJG7BVVB6ZHF","short_pith_number":"pith:4RABHY6P","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"},"canonical_sha256":"e44013e3cf26653bac0937c35a87d9396a23d8f6574ca5f5cbc58d9e0ffd9043","source":{"kind":"arxiv","id":"1708.05144","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05144","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05144v2","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05144","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"pith_short_12","alias_value":"4RABHY6PEZST","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4RABHY6PEZSTXLAJ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4RABHY6P","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4RABHY6PEZSTXLAJG7BVVB6ZHF","target":"record","payload":{"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"},"canonical_sha256":"e44013e3cf26653bac0937c35a87d9396a23d8f6574ca5f5cbc58d9e0ffd9043","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"},"source_kind":"arxiv","source_id":"1708.05144","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:37:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2+tYp3rBUt4CD7mOG+SDcuV/XoxarK4X1I3ITcqK/zFHAZhD+KV72/vPG/gYKQDs4I+9Szn/EfjWECPuTIH3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:45:52.701553Z"},"content_sha256":"1936f09d077bdaad15dfeefdb666f2bae73e22638181273f7877f771a17aa228","schema_version":"1.0","event_id":"sha256:1936f09d077bdaad15dfeefdb666f2bae73e22638181273f7877f771a17aa228"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4RABHY6PEZSTXLAJG7BVVB6ZHF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:37:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KExZpk0M8XdT1yD8peGWxLakbmQiJLnH9cc8Ls0Y3jiSh6ldBvMsrCBan9FCuBNIi3LTlk9WmpnmclQB37ixCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:45:52.702225Z"},"content_sha256":"9d3fccfd5537b71b3b9f3548073a5837df14fc924b25db61ac7a58f9c40f5839","schema_version":"1.0","event_id":"sha256:9d3fccfd5537b71b3b9f3548073a5837df14fc924b25db61ac7a58f9c40f5839"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/bundle.json","state_url":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/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":"2026-05-25T18:45:52Z","links":{"resolver":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF","bundle":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/bundle.json","state":"https://pith.science/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4RABHY6PEZSTXLAJG7BVVB6ZHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4RABHY6PEZSTXLAJG7BVVB6ZHF","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":"dd313e5c3a51b22d31802072a9c22dd72af8c6baa98f4303705ccab5ba9588d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-17T06:14:48Z","title_canon_sha256":"cf84b3cc746fb4aece830ed446435740ca16287250318e453dc64ef5877cd7cd"},"schema_version":"1.0","source":{"id":"1708.05144","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.05144","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"arxiv_version","alias_value":"1708.05144v2","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.05144","created_at":"2026-05-18T00:37:50Z"},{"alias_kind":"pith_short_12","alias_value":"4RABHY6PEZST","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4RABHY6PEZSTXLAJ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4RABHY6P","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:9d3fccfd5537b71b3b9f3548073a5837df14fc924b25db61ac7a58f9c40f5839","target":"graph","created_at":"2026-05-18T00:37:50Z","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"},"paper":{"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","authors_text":"Elman Mansimov, Jimmy Ba, Roger Grosse, Shun Liao, Yuhuai Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-17T06:14:48Z","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.05144","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":"sha256:1936f09d077bdaad15dfeefdb666f2bae73e22638181273f7877f771a17aa228","target":"record","created_at":"2026-05-18T00:37:50Z","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":"dd313e5c3a51b22d31802072a9c22dd72af8c6baa98f4303705ccab5ba9588d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-17T06:14:48Z","title_canon_sha256":"cf84b3cc746fb4aece830ed446435740ca16287250318e453dc64ef5877cd7cd"},"schema_version":"1.0","source":{"id":"1708.05144","kind":"arxiv","version":2}},"canonical_sha256":"e44013e3cf26653bac0937c35a87d9396a23d8f6574ca5f5cbc58d9e0ffd9043","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e44013e3cf26653bac0937c35a87d9396a23d8f6574ca5f5cbc58d9e0ffd9043","first_computed_at":"2026-05-18T00:37:50.217876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:50.217876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oChladpQH6q2dE+Tx5k64ZarvpLqgGckp7nJjPo20LGG1meIbQalTuZAq3xWa62o957wLtMmla/yzmSBJsc7DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:50.218502Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.05144","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1936f09d077bdaad15dfeefdb666f2bae73e22638181273f7877f771a17aa228","sha256:9d3fccfd5537b71b3b9f3548073a5837df14fc924b25db61ac7a58f9c40f5839"],"state_sha256":"19fd68ee0171a7d1e9654f620fcb5c3f9e32716f4661585b8348aeca2bdae7ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kEABmfksSlQY+YZmbGt/bBqAshApkSWJmwwj9zzaqVN/VrIGYSbCys9zWExfaVEIsJhYoSNBpPtFroAVfmxmDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:45:52.705702Z","bundle_sha256":"a3c76646ee95538364a772ab4de2614efeb9ef2537d9e39131b1fb6aa2f1b903"}}