{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GIRNQE5Z7ZGVEZS7PB6LHQLB7M","short_pith_number":"pith:GIRNQE5Z","schema_version":"1.0","canonical_sha256":"3222d813b9fe4d52665f787cb3c161fb1da993d38d920e2716a638e0d9cb5c0c","source":{"kind":"arxiv","id":"1810.06509","version":2},"attestation_state":"computed","paper":{"title":"Predictor-Corrector Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Ching-An Cheng, Nathan Ratliff, Xinyan Yan","submitted_at":"2018-10-15T16:44:48Z","abstract_excerpt":"We present a predictor-corrector framework, called PicCoLO, that can transform a first-order model-free reinforcement or imitation learning algorithm into a new hybrid method that leverages predictive models to accelerate policy learning. The new \"PicCoLOed\" algorithm optimizes a policy by recursively repeating two steps: In the Prediction Step, the learner uses a model to predict the unseen future gradient and then applies the predicted estimate to update the policy; in the Correction Step, the learner runs the updated policy in the environment, receives the true gradient, and then corrects 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":"1810.06509","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-15T16:44:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e5e2ee743bb32993e319b5990cee319f6407969c21aec7dccc700678ca878116","abstract_canon_sha256":"a3158273b9a24d839e07a803e3b7b0862a6d094826d51ac19f01fc302f666a59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:09.509735Z","signature_b64":"mHfbKx2Xw4IuhFAN3UMFn94kl4AeZPqzQe63JOUJSJK2Hu5+v+RdsNdrGlhpJjUpJUgXJ/0Etf+qkHYxd8WyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3222d813b9fe4d52665f787cb3c161fb1da993d38d920e2716a638e0d9cb5c0c","last_reissued_at":"2026-05-17T23:45:09.509146Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:09.509146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predictor-Corrector Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Ching-An Cheng, Nathan Ratliff, Xinyan Yan","submitted_at":"2018-10-15T16:44:48Z","abstract_excerpt":"We present a predictor-corrector framework, called PicCoLO, that can transform a first-order model-free reinforcement or imitation learning algorithm into a new hybrid method that leverages predictive models to accelerate policy learning. The new \"PicCoLOed\" algorithm optimizes a policy by recursively repeating two steps: In the Prediction Step, the learner uses a model to predict the unseen future gradient and then applies the predicted estimate to update the policy; in the Correction Step, the learner runs the updated policy in the environment, receives the true gradient, and then corrects t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06509","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":"1810.06509","created_at":"2026-05-17T23:45:09.509239+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.06509v2","created_at":"2026-05-17T23:45:09.509239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06509","created_at":"2026-05-17T23:45:09.509239+00:00"},{"alias_kind":"pith_short_12","alias_value":"GIRNQE5Z7ZGV","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GIRNQE5Z7ZGVEZS7","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GIRNQE5Z","created_at":"2026-05-18T12:32:25.280505+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/GIRNQE5Z7ZGVEZS7PB6LHQLB7M","json":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M.json","graph_json":"https://pith.science/api/pith-number/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/graph.json","events_json":"https://pith.science/api/pith-number/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/events.json","paper":"https://pith.science/paper/GIRNQE5Z"},"agent_actions":{"view_html":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M","download_json":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M.json","view_paper":"https://pith.science/paper/GIRNQE5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.06509&json=true","fetch_graph":"https://pith.science/api/pith-number/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/graph.json","fetch_events":"https://pith.science/api/pith-number/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/action/storage_attestation","attest_author":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/action/author_attestation","sign_citation":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/action/citation_signature","submit_replication":"https://pith.science/pith/GIRNQE5Z7ZGVEZS7PB6LHQLB7M/action/replication_record"}},"created_at":"2026-05-17T23:45:09.509239+00:00","updated_at":"2026-05-17T23:45:09.509239+00:00"}