{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LYJOXZNRC7MUB2RMZ5Y6SK7MA4","short_pith_number":"pith:LYJOXZNR","schema_version":"1.0","canonical_sha256":"5e12ebe5b117d940ea2ccf71e92bec071947271d6fd912093b23cc76be7f6d9e","source":{"kind":"arxiv","id":"2412.00086","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Balakumar Sundaralingam, Byron Boots, Mohak Bhardwaj, Neel Jawale","submitted_at":"2024-11-27T03:33:42Z","abstract_excerpt":"We investigate the problem of teaching a robot manipulator to perform dynamic non-prehensile object transport, also known as the `robot waiter' task, from a limited set of real-world demonstrations. We propose an approach that combines batch reinforcement learning (RL) with model-predictive control (MPC) by pretraining an ensemble of value functions from demonstration data, and utilizing them online within an uncertainty-aware MPC scheme to ensure robustness to limited data coverage. Our approach is straightforward to integrate with off-the-shelf MPC frameworks and enables learning solely from"},"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":"2412.00086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T03:33:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bd2d26355af9f94ca70e6591172c3ec78c46e8279fbd753e41d9a311b2943d2c","abstract_canon_sha256":"5b1caf4a0f2c5aed2f5735583b20894a30aed1225235221bafa963a9e6339c31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:36.102430Z","signature_b64":"4/u/J+EOqMPiiKaj0VXIkDSPuz7MbqaBAZzp49DCmpYY0ygdL535fsF2QT0UZRfe/mm+BTyL+OUBkBlfjQFIAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e12ebe5b117d940ea2ccf71e92bec071947271d6fd912093b23cc76be7f6d9e","last_reissued_at":"2026-07-05T09:42:36.102013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:36.102013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Balakumar Sundaralingam, Byron Boots, Mohak Bhardwaj, Neel Jawale","submitted_at":"2024-11-27T03:33:42Z","abstract_excerpt":"We investigate the problem of teaching a robot manipulator to perform dynamic non-prehensile object transport, also known as the `robot waiter' task, from a limited set of real-world demonstrations. We propose an approach that combines batch reinforcement learning (RL) with model-predictive control (MPC) by pretraining an ensemble of value functions from demonstration data, and utilizing them online within an uncertainty-aware MPC scheme to ensure robustness to limited data coverage. Our approach is straightforward to integrate with off-the-shelf MPC frameworks and enables learning solely from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00086","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/2412.00086/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":"2412.00086","created_at":"2026-07-05T09:42:36.102075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00086v1","created_at":"2026-07-05T09:42:36.102075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00086","created_at":"2026-07-05T09:42:36.102075+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYJOXZNRC7MU","created_at":"2026-07-05T09:42:36.102075+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYJOXZNRC7MUB2RM","created_at":"2026-07-05T09:42:36.102075+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYJOXZNR","created_at":"2026-07-05T09:42:36.102075+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/LYJOXZNRC7MUB2RMZ5Y6SK7MA4","json":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4.json","graph_json":"https://pith.science/api/pith-number/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/graph.json","events_json":"https://pith.science/api/pith-number/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/events.json","paper":"https://pith.science/paper/LYJOXZNR"},"agent_actions":{"view_html":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4","download_json":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4.json","view_paper":"https://pith.science/paper/LYJOXZNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00086&json=true","fetch_graph":"https://pith.science/api/pith-number/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/graph.json","fetch_events":"https://pith.science/api/pith-number/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/action/storage_attestation","attest_author":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/action/author_attestation","sign_citation":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/action/citation_signature","submit_replication":"https://pith.science/pith/LYJOXZNRC7MUB2RMZ5Y6SK7MA4/action/replication_record"}},"created_at":"2026-07-05T09:42:36.102075+00:00","updated_at":"2026-07-05T09:42:36.102075+00:00"}