{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UOVNUU56BREHS5TZXDOIY4XBCA","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":"c7cd0b69e6574f6c7c17e2df19b53933d8b0f8853d062a321c93af8d28276278","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T17:09:18Z","title_canon_sha256":"09ce710ab002e352e8e3cbf43e07ef4bda79051ca8fe7c6c289448a0b61697e1"},"schema_version":"1.0","source":{"id":"1811.01848","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01848","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01848v3","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01848","created_at":"2026-05-17T23:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"UOVNUU56BREH","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UOVNUU56BREHS5TZ","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UOVNUU56","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:265710fda67bcfb9c3ffd12839d390e0e773402f2152be65a55851ba604f5e7f","target":"graph","created_at":"2026-05-17T23:55:28Z","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":"We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local trajectory optimization can cope with approximation errors in the value function, and can stabilize and accelerate value function learning. Conversely, we also study how approximate value functions can help reduce the planning horizon and allow for better policies beyond local soluti","authors_text":"Aravind Rajeswaran, Emanuel Todorov, Igor Mordatch, Kendall Lowrey, Sham Kakade","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T17:09:18Z","title":"Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01848","kind":"arxiv","version":3},"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:ab045dcd56659cc75572f8bfe866580981efd5095da75c7a751b426086da5cd9","target":"record","created_at":"2026-05-17T23:55:28Z","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":"c7cd0b69e6574f6c7c17e2df19b53933d8b0f8853d062a321c93af8d28276278","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-05T17:09:18Z","title_canon_sha256":"09ce710ab002e352e8e3cbf43e07ef4bda79051ca8fe7c6c289448a0b61697e1"},"schema_version":"1.0","source":{"id":"1811.01848","kind":"arxiv","version":3}},"canonical_sha256":"a3aada53be0c48797679b8dc8c72e1103f62c76dc0cb08ed44032757867cbbbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3aada53be0c48797679b8dc8c72e1103f62c76dc0cb08ed44032757867cbbbc","first_computed_at":"2026-05-17T23:55:28.729057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:28.729057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3YVIp0t3l+F2YUKsqFiDACDoVUpANzumcTi8Pw3pzesV70Trzk1LNAVb+Y5QMXyEVDoPteW7UOiFMsfrLJ7mDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:28.729660Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.01848","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab045dcd56659cc75572f8bfe866580981efd5095da75c7a751b426086da5cd9","sha256:265710fda67bcfb9c3ffd12839d390e0e773402f2152be65a55851ba604f5e7f"],"state_sha256":"dbec80962ae65633d7604d90310ceacc1ce5b3beeb0ae95d2d922888617fab1d"}