{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5QAPM7HBB4UNDXEBAARF3IDHBW","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":"4f953925129bddacff5bcb31f2576b0021561bbe5d187ab475087a9704629188","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-22T15:56:00Z","title_canon_sha256":"0a59ba377147a67fe51bd1b3c9000a3585cba5b27ef90c2d40257faad92ee7d8"},"schema_version":"1.0","source":{"id":"2001.08092","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.08092","created_at":"2026-07-05T00:35:07Z"},{"alias_kind":"arxiv_version","alias_value":"2001.08092v1","created_at":"2026-07-05T00:35:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08092","created_at":"2026-07-05T00:35:07Z"},{"alias_kind":"pith_short_12","alias_value":"5QAPM7HBB4UN","created_at":"2026-07-05T00:35:07Z"},{"alias_kind":"pith_short_16","alias_value":"5QAPM7HBB4UNDXEB","created_at":"2026-07-05T00:35:07Z"},{"alias_kind":"pith_short_8","alias_value":"5QAPM7HB","created_at":"2026-07-05T00:35:07Z"}],"graph_snapshots":[{"event_id":"sha256:26fd3fe270913ebacf92533626e8d96bd789be1cb48fcf2d049e87bbe805575a","target":"graph","created_at":"2026-07-05T00:35:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2001.08092/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is to present a method for simultaneous trajectory and local stabilizing policy optimization to generate local policies for trajectory-centric model-based reinforcement learning (MBRL). This is motivated by the fact that global policy optimization for non-linear systems could be a very challenging problem both algorithmically and numerically. However, a lot of robotic manipulation tasks are trajectory-centric, and thus do not require a global model or policy. Due to inaccuracies in the learned model estimates, an open-loop trajectory optimization process mostly results i","authors_text":"Arvind U. Raghunathan, Daniel Nikovski, Devesh K. Jha, Diego Romeres, Frank L. Lewis, Mouhacine Benosman, Patrik Kolaric","cross_cats":["cs.RO","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-22T15:56:00Z","title":"Local Policy Optimization for Trajectory-Centric Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08092","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":"sha256:72e3deb79c77b1da6b7dfd84e44d0c7d4b99f5d5ae0a1c7192a8458121a06fe3","target":"record","created_at":"2026-07-05T00:35:07Z","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":"4f953925129bddacff5bcb31f2576b0021561bbe5d187ab475087a9704629188","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-22T15:56:00Z","title_canon_sha256":"0a59ba377147a67fe51bd1b3c9000a3585cba5b27ef90c2d40257faad92ee7d8"},"schema_version":"1.0","source":{"id":"2001.08092","kind":"arxiv","version":1}},"canonical_sha256":"ec00f67ce10f28d1dc8100225da0670d89a7366e38c80fbad9c6765209b91d17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec00f67ce10f28d1dc8100225da0670d89a7366e38c80fbad9c6765209b91d17","first_computed_at":"2026-07-05T00:35:07.669440Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:07.669440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOqoR0NoGfCTXyVdrFS883mlradWhxhFwks73aAgHIeidXvG3q7lpW3WwrUWVtD+onYI5Fii5vr+SgKbzmNFBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:07.669841Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.08092","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72e3deb79c77b1da6b7dfd84e44d0c7d4b99f5d5ae0a1c7192a8458121a06fe3","sha256:26fd3fe270913ebacf92533626e8d96bd789be1cb48fcf2d049e87bbe805575a"],"state_sha256":"a4f2a4f0d98d4af9d5a54f5814a485b46e5d231c42da842a27e0220b4fc358d5"}