{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:TDPKRIQUU3BU6NOSUPKFT7ADDM","short_pith_number":"pith:TDPKRIQU","canonical_record":{"source":{"id":"1607.04614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T18:54:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2e5473d5ca87aea223f543cd02ede56fe4f1a70f44a59f5f66fbf46ba96908f3","abstract_canon_sha256":"14b08aceac1a7ce7d66f4bf8f137e9fbae45f87b9ca12939795a82e4f6a14c59"},"schema_version":"1.0"},"canonical_sha256":"98dea8a214a6c34f35d2a3d459fc031b25de50fb861b1b1d3daf2e85cae7ac52","source":{"kind":"arxiv","id":"1607.04614","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.04614","created_at":"2026-05-18T01:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"1607.04614v1","created_at":"2026-05-18T01:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04614","created_at":"2026-05-18T01:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"TDPKRIQUU3BU","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"TDPKRIQUU3BU6NOS","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"TDPKRIQU","created_at":"2026-05-18T12:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:TDPKRIQUU3BU6NOSUPKFT7ADDM","target":"record","payload":{"canonical_record":{"source":{"id":"1607.04614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T18:54:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2e5473d5ca87aea223f543cd02ede56fe4f1a70f44a59f5f66fbf46ba96908f3","abstract_canon_sha256":"14b08aceac1a7ce7d66f4bf8f137e9fbae45f87b9ca12939795a82e4f6a14c59"},"schema_version":"1.0"},"canonical_sha256":"98dea8a214a6c34f35d2a3d459fc031b25de50fb861b1b1d3daf2e85cae7ac52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:00.761784Z","signature_b64":"U8G4wU17qffG3tNTpvCcOWZDMaIDHlD5QQW36i8LWGmO0hfEZo8p8vOj9KpUO4YKMenUqA3g+kt5WMgsZYTdBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98dea8a214a6c34f35d2a3d459fc031b25de50fb861b1b1d3daf2e85cae7ac52","last_reissued_at":"2026-05-18T01:11:00.761042Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:00.761042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.04614","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dmQDCr/voQr9mT7A8FaU8XRKpehAjkzj8gmkMbxjo2tZfBdOVlSlAjnztlhCJx+smDPxsDWI4ju1MzE94VQLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T07:07:24.627000Z"},"content_sha256":"92f26fa488316381aa21399d11cbba19c161c23c9e99fe2c78092a451507a1f4","schema_version":"1.0","event_id":"sha256:92f26fa488316381aa21399d11cbba19c161c23c9e99fe2c78092a451507a1f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:TDPKRIQUU3BU6NOSUPKFT7ADDM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guided Policy Search as Approximate Mirror Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Sergey Levine, William Montgomery","submitted_at":"2016-07-15T18:54:15Z","abstract_excerpt":"Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised learning to train the policy to mimic a \"teacher\" algorithm, such as a trajectory optimizer or a trajectory-centric reinforcement learning method. Guided policy search methods provide asymptotic local convergence guarantees by construction, but it is not clear how much the policy improves within a small, finite number of iterations. We show that guided policy s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04614","kind":"arxiv","version":1},"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":"2026-05-18T01:11:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wXW6MwrXlCOpn2u6PUkw2XZCCvPNc1wClitXeGjFc6MaHM9J3zQ2e87z4KdF6ypYx0GRYJ24MGhg8Vguu5bWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T07:07:24.627387Z"},"content_sha256":"a5d9a26161f87293986492ca92ae37bb044403bcd4a2b464f146bb71fa0d80c9","schema_version":"1.0","event_id":"sha256:a5d9a26161f87293986492ca92ae37bb044403bcd4a2b464f146bb71fa0d80c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/bundle.json","state_url":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/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":"2026-06-12T07:07:24Z","links":{"resolver":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM","bundle":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/bundle.json","state":"https://pith.science/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TDPKRIQUU3BU6NOSUPKFT7ADDM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:TDPKRIQUU3BU6NOSUPKFT7ADDM","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":"14b08aceac1a7ce7d66f4bf8f137e9fbae45f87b9ca12939795a82e4f6a14c59","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T18:54:15Z","title_canon_sha256":"2e5473d5ca87aea223f543cd02ede56fe4f1a70f44a59f5f66fbf46ba96908f3"},"schema_version":"1.0","source":{"id":"1607.04614","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.04614","created_at":"2026-05-18T01:11:00Z"},{"alias_kind":"arxiv_version","alias_value":"1607.04614v1","created_at":"2026-05-18T01:11:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04614","created_at":"2026-05-18T01:11:00Z"},{"alias_kind":"pith_short_12","alias_value":"TDPKRIQUU3BU","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"TDPKRIQUU3BU6NOS","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"TDPKRIQU","created_at":"2026-05-18T12:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:a5d9a26161f87293986492ca92ae37bb044403bcd4a2b464f146bb71fa0d80c9","target":"graph","created_at":"2026-05-18T01:11:00Z","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":"Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised learning to train the policy to mimic a \"teacher\" algorithm, such as a trajectory optimizer or a trajectory-centric reinforcement learning method. Guided policy search methods provide asymptotic local convergence guarantees by construction, but it is not clear how much the policy improves within a small, finite number of iterations. We show that guided policy s","authors_text":"Sergey Levine, William Montgomery","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T18:54:15Z","title":"Guided Policy Search as Approximate Mirror Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04614","kind":"arxiv","version":1},"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":"sha256:92f26fa488316381aa21399d11cbba19c161c23c9e99fe2c78092a451507a1f4","target":"record","created_at":"2026-05-18T01:11:00Z","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":"14b08aceac1a7ce7d66f4bf8f137e9fbae45f87b9ca12939795a82e4f6a14c59","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-07-15T18:54:15Z","title_canon_sha256":"2e5473d5ca87aea223f543cd02ede56fe4f1a70f44a59f5f66fbf46ba96908f3"},"schema_version":"1.0","source":{"id":"1607.04614","kind":"arxiv","version":1}},"canonical_sha256":"98dea8a214a6c34f35d2a3d459fc031b25de50fb861b1b1d3daf2e85cae7ac52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98dea8a214a6c34f35d2a3d459fc031b25de50fb861b1b1d3daf2e85cae7ac52","first_computed_at":"2026-05-18T01:11:00.761042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:11:00.761042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U8G4wU17qffG3tNTpvCcOWZDMaIDHlD5QQW36i8LWGmO0hfEZo8p8vOj9KpUO4YKMenUqA3g+kt5WMgsZYTdBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:11:00.761784Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.04614","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92f26fa488316381aa21399d11cbba19c161c23c9e99fe2c78092a451507a1f4","sha256:a5d9a26161f87293986492ca92ae37bb044403bcd4a2b464f146bb71fa0d80c9"],"state_sha256":"8b32ef2e5130af0d47d642ec693b5ec6097f2481e44b2841bd181f0f8033fda6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzIZknEbYfCDdnuZIc3ksEq0ioibH/J23uqFqCrh1gt7FA5HWCs3atJ1yawCBc1AVQklhdQFGLprd1lnkCqVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T07:07:24.629671Z","bundle_sha256":"52137c7eb8108ffc818f995fa7aaace4bb28c4f3fd854769511b42f2d3983d29"}}