{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PXJ2UQQVJ2ZJ5CGVGVOT65G4BH","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":"bbdcc4da13106cc868d24fdf77725c06c06f10252fd2a054e6a6a07a15eb3cfb","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T18:13:03Z","title_canon_sha256":"a1835ca2be4269213f0852e21980043362d61e0ec3ce4512fee89dd1e84ba78f"},"schema_version":"1.0","source":{"id":"1708.02596","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.02596","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"1708.02596v2","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02596","created_at":"2026-05-18T00:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"PXJ2UQQVJ2ZJ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PXJ2UQQVJ2ZJ5CGV","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PXJ2UQQV","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:a54519c153364170b3a0d3515b36ccb2962c022c21fef826b5ca04325527fb2b","target":"graph","created_at":"2026-05-18T00:29:05Z","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":"Model-free deep reinforcement learning algorithms have been shown to be capable of learning a wide range of robotic skills, but typically require a very large number of samples to achieve good performance. Model-based algorithms, in principle, can provide for much more efficient learning, but have proven difficult to extend to expressive, high-capacity models such as deep neural networks. In this work, we demonstrate that medium-sized neural network models can in fact be combined with model predictive control (MPC) to achieve excellent sample complexity in a model-based reinforcement learning ","authors_text":"Anusha Nagabandi, Gregory Kahn, Ronald S. Fearing, Sergey Levine","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T18:13:03Z","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02596","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:f02198722330e7c352e59730801b68ff70a58b242590b0ce645b0ba721eb1dd0","target":"record","created_at":"2026-05-18T00:29:05Z","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":"bbdcc4da13106cc868d24fdf77725c06c06f10252fd2a054e6a6a07a15eb3cfb","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-08T18:13:03Z","title_canon_sha256":"a1835ca2be4269213f0852e21980043362d61e0ec3ce4512fee89dd1e84ba78f"},"schema_version":"1.0","source":{"id":"1708.02596","kind":"arxiv","version":2}},"canonical_sha256":"7dd3aa42154eb29e88d5355d3f74dc09c04fa10d4615977b93e8cd0f800fdcd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dd3aa42154eb29e88d5355d3f74dc09c04fa10d4615977b93e8cd0f800fdcd3","first_computed_at":"2026-05-18T00:29:05.549860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:05.549860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q5uuHaMHng5AGpjzOkl43SwdFZTBnTeCFD0FnjCs1SR0AvWTZWcyEA7OCx2u0+3go8kw89s6woUTxb5ejZYMCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:05.550499Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.02596","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f02198722330e7c352e59730801b68ff70a58b242590b0ce645b0ba721eb1dd0","sha256:a54519c153364170b3a0d3515b36ccb2962c022c21fef826b5ca04325527fb2b"],"state_sha256":"ac17ac62683fd7cfcafbd8960de591af3ded56f96982465ca2541fe74f5927f4"}