{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4T4TXYAQRKLBVPAIL7YQRUU7A7","short_pith_number":"pith:4T4TXYAQ","schema_version":"1.0","canonical_sha256":"e4f93be0108a961abc085ff108d29f07ea0c6322cc6a9f91284f9d1120501c56","source":{"kind":"arxiv","id":"2112.02999","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Sagi, Aman Singh, Chandravaran Kunjeti, Himanshu Lodha, Prakhar Goel, Shalabh Bhatnagar, Shishir Kolathaya, Soumya R. Samineni, Utkarsh A. Mishra","submitted_at":"2021-11-04T09:24:47Z","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"},"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":"2112.02999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2021-11-04T09:24:47Z","cross_cats_sorted":[],"title_canon_sha256":"36c583272d058ea211c11a122ee685d88a9de02790af4f972d8607df755f5563","abstract_canon_sha256":"e2786f1161efba2ca261c9389c799bfd08ad3db4f3c914a6e77f07d686aa6bed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:00.404272Z","signature_b64":"0I0b7KTa587l8I1wwwY6qPW9y35t5+/NNGGQW6xepfFYPNfzUzIa87VAGmhXC4+0CRFhx1NsgkiIPI3hWWslCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4f93be0108a961abc085ff108d29f07ea0c6322cc6a9f91284f9d1120501c56","last_reissued_at":"2026-07-05T03:38:00.403813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:00.403813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Aditya Sagi, Aman Singh, Chandravaran Kunjeti, Himanshu Lodha, Prakhar Goel, Shalabh Bhatnagar, Shishir Kolathaya, Soumya R. Samineni, Utkarsh A. Mishra","submitted_at":"2021-11-04T09:24:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.02999","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.02999/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2112.02999","created_at":"2026-07-05T03:38:00.403866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.02999v1","created_at":"2026-07-05T03:38:00.403866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.02999","created_at":"2026-07-05T03:38:00.403866+00:00"},{"alias_kind":"pith_short_12","alias_value":"4T4TXYAQRKLB","created_at":"2026-07-05T03:38:00.403866+00:00"},{"alias_kind":"pith_short_16","alias_value":"4T4TXYAQRKLBVPAI","created_at":"2026-07-05T03:38:00.403866+00:00"},{"alias_kind":"pith_short_8","alias_value":"4T4TXYAQ","created_at":"2026-07-05T03:38:00.403866+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/4T4TXYAQRKLBVPAIL7YQRUU7A7","json":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7.json","graph_json":"https://pith.science/api/pith-number/4T4TXYAQRKLBVPAIL7YQRUU7A7/graph.json","events_json":"https://pith.science/api/pith-number/4T4TXYAQRKLBVPAIL7YQRUU7A7/events.json","paper":"https://pith.science/paper/4T4TXYAQ"},"agent_actions":{"view_html":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7","download_json":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7.json","view_paper":"https://pith.science/paper/4T4TXYAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.02999&json=true","fetch_graph":"https://pith.science/api/pith-number/4T4TXYAQRKLBVPAIL7YQRUU7A7/graph.json","fetch_events":"https://pith.science/api/pith-number/4T4TXYAQRKLBVPAIL7YQRUU7A7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7/action/storage_attestation","attest_author":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7/action/author_attestation","sign_citation":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7/action/citation_signature","submit_replication":"https://pith.science/pith/4T4TXYAQRKLBVPAIL7YQRUU7A7/action/replication_record"}},"created_at":"2026-07-05T03:38:00.403866+00:00","updated_at":"2026-07-05T03:38:00.403866+00:00"}