{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LYJOXZNRC7MUB2RMZ5Y6SK7MA4","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":"5b1caf4a0f2c5aed2f5735583b20894a30aed1225235221bafa963a9e6339c31","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T03:33:42Z","title_canon_sha256":"bd2d26355af9f94ca70e6591172c3ec78c46e8279fbd753e41d9a311b2943d2c"},"schema_version":"1.0","source":{"id":"2412.00086","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00086","created_at":"2026-07-05T09:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00086v1","created_at":"2026-07-05T09:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00086","created_at":"2026-07-05T09:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"LYJOXZNRC7MU","created_at":"2026-07-05T09:42:36Z"},{"alias_kind":"pith_short_16","alias_value":"LYJOXZNRC7MUB2RM","created_at":"2026-07-05T09:42:36Z"},{"alias_kind":"pith_short_8","alias_value":"LYJOXZNR","created_at":"2026-07-05T09:42:36Z"}],"graph_snapshots":[{"event_id":"sha256:e4f8cd6db6da6d70b353c203beda4a20f7f98dab50d834852f359b284cbb266a","target":"graph","created_at":"2026-07-05T09:42:36Z","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/2412.00086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Balakumar Sundaralingam, Byron Boots, Mohak Bhardwaj, Neel Jawale","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T03:33:42Z","title":"Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00086","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":"sha256:8959e20d46b6efebd662213bee4bd8a4de2026a0e2a0505f274d01a40847298c","target":"record","created_at":"2026-07-05T09:42:36Z","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":"5b1caf4a0f2c5aed2f5735583b20894a30aed1225235221bafa963a9e6339c31","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-11-27T03:33:42Z","title_canon_sha256":"bd2d26355af9f94ca70e6591172c3ec78c46e8279fbd753e41d9a311b2943d2c"},"schema_version":"1.0","source":{"id":"2412.00086","kind":"arxiv","version":1}},"canonical_sha256":"5e12ebe5b117d940ea2ccf71e92bec071947271d6fd912093b23cc76be7f6d9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e12ebe5b117d940ea2ccf71e92bec071947271d6fd912093b23cc76be7f6d9e","first_computed_at":"2026-07-05T09:42:36.102013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:36.102013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4/u/J+EOqMPiiKaj0VXIkDSPuz7MbqaBAZzp49DCmpYY0ygdL535fsF2QT0UZRfe/mm+BTyL+OUBkBlfjQFIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:36.102430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00086","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8959e20d46b6efebd662213bee4bd8a4de2026a0e2a0505f274d01a40847298c","sha256:e4f8cd6db6da6d70b353c203beda4a20f7f98dab50d834852f359b284cbb266a"],"state_sha256":"7737c50fe38bf8eaeabd8778ae7f6a204bba0ec41c6e45698e8631527d28fe43"}