{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4T4TXYAQRKLBVPAIL7YQRUU7A7","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":"e2786f1161efba2ca261c9389c799bfd08ad3db4f3c914a6e77f07d686aa6bed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-04T09:24:47Z","title_canon_sha256":"36c583272d058ea211c11a122ee685d88a9de02790af4f972d8607df755f5563"},"schema_version":"1.0","source":{"id":"2112.02999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.02999","created_at":"2026-07-05T03:38:00Z"},{"alias_kind":"arxiv_version","alias_value":"2112.02999v1","created_at":"2026-07-05T03:38:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02999","created_at":"2026-07-05T03:38:00Z"},{"alias_kind":"pith_short_12","alias_value":"4T4TXYAQRKLB","created_at":"2026-07-05T03:38:00Z"},{"alias_kind":"pith_short_16","alias_value":"4T4TXYAQRKLBVPAI","created_at":"2026-07-05T03:38:00Z"},{"alias_kind":"pith_short_8","alias_value":"4T4TXYAQ","created_at":"2026-07-05T03:38:00Z"}],"graph_snapshots":[{"event_id":"sha256:c0f2eff794e1a3955ef39a59be8d406ebfbad2f34b997a07f688b152409552ce","target":"graph","created_at":"2026-07-05T03:38:00Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2112.02999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works in Reinforcement Learning (RL) combine model-free (Mf)-RL algorithms with model-based (Mb)-RL approaches to get the best from both: asymptotic performance of Mf-RL and high sample-efficiency of Mb-RL. Inspired by these works, we propose a hierarchical framework that integrates online learning for the Mb-trajectory optimization with off-policy methods for the Mf-RL. In particular, two loops are proposed, where the Dynamic Mirror Descent based Model Predictive Control (DMD-MPC) is used as the inner loop Mb-RL to obtain an optimal sequence of actions. These actions are in turn used t","authors_text":"Aditya Sagi, Aman Singh, Chandravaran Kunjeti, Himanshu Lodha, Prakhar Goel, Shalabh Bhatnagar, Shishir Kolathaya, Soumya R. Samineni, Utkarsh A. Mishra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-04T09:24:47Z","title":"Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02999","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":"sha256:5dbe32202cfc76470d96108f2188be9f7077286ea0d2819512d8855fcbceae83","target":"record","created_at":"2026-07-05T03:38:00Z","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":"e2786f1161efba2ca261c9389c799bfd08ad3db4f3c914a6e77f07d686aa6bed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-04T09:24:47Z","title_canon_sha256":"36c583272d058ea211c11a122ee685d88a9de02790af4f972d8607df755f5563"},"schema_version":"1.0","source":{"id":"2112.02999","kind":"arxiv","version":1}},"canonical_sha256":"e4f93be0108a961abc085ff108d29f07ea0c6322cc6a9f91284f9d1120501c56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4f93be0108a961abc085ff108d29f07ea0c6322cc6a9f91284f9d1120501c56","first_computed_at":"2026-07-05T03:38:00.403813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:00.403813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0I0b7KTa587l8I1wwwY6qPW9y35t5+/NNGGQW6xepfFYPNfzUzIa87VAGmhXC4+0CRFhx1NsgkiIPI3hWWslCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:00.404272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.02999","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dbe32202cfc76470d96108f2188be9f7077286ea0d2819512d8855fcbceae83","sha256:c0f2eff794e1a3955ef39a59be8d406ebfbad2f34b997a07f688b152409552ce"],"state_sha256":"da53a9cb9ace48bab462337c5345dd627420b07848132ead8d0cbfe31f5fe15e"}