{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:COIVWEKU63CRX6JJR476DZHSLD","short_pith_number":"pith:COIVWEKU","schema_version":"1.0","canonical_sha256":"13915b1154f6c51bf9298f3fe1e4f258e20dff2b7ec3b26bde990577aa53a0e6","source":{"kind":"arxiv","id":"2606.05687","version":1},"attestation_state":"computed","paper":{"title":"Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Aaron D. Ames, J\\'an Drgo\\v{n}a, Junheng Li, Liang Wu, Lizhi Yang, Sergio A. Esteban","submitted_at":"2026-06-04T04:12:47Z","abstract_excerpt":"In humanoid motion control, model predictive control (MPC) offers physically grounded prediction and constraint handling, while reinforcement learning (RL) enables robust whole-body skills through large-scale simulation. However, using MPC inside RL often requires time-consuming problem construction or excessive training overhead, making such frameworks difficult to justify in practice. This work studies efficient training-time MPC guidance for humanoid locomotion and manipulation, termed MPC-RL. We introduce a centroidal-dynamics MPC reward formulation that leverages guidance from MPC traject"},"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":"2606.05687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-04T04:12:47Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"712550cddf86bc8a4cbb551b363f571aadbabc61ce0972db3f6d016e2c895d4b","abstract_canon_sha256":"50c42c45c2f3bbd8ee91d0e96885e5f8245eb979f34a35e5b5783dde18c4b586"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:59.324257Z","signature_b64":"WLnSsHcA0JEgng9+4eZFIlQY19zD/wZ0FJOQ1HS16SJYqmVLlmDnLDCD45Paf2mfNWNr9JF5h6bKwTDnFO8vCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13915b1154f6c51bf9298f3fe1e4f258e20dff2b7ec3b26bde990577aa53a0e6","last_reissued_at":"2026-06-05T01:14:59.323626Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:59.323626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Aaron D. Ames, J\\'an Drgo\\v{n}a, Junheng Li, Liang Wu, Lizhi Yang, Sergio A. Esteban","submitted_at":"2026-06-04T04:12:47Z","abstract_excerpt":"In humanoid motion control, model predictive control (MPC) offers physically grounded prediction and constraint handling, while reinforcement learning (RL) enables robust whole-body skills through large-scale simulation. However, using MPC inside RL often requires time-consuming problem construction or excessive training overhead, making such frameworks difficult to justify in practice. This work studies efficient training-time MPC guidance for humanoid locomotion and manipulation, termed MPC-RL. We introduce a centroidal-dynamics MPC reward formulation that leverages guidance from MPC traject"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05687","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/2606.05687/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":"2606.05687","created_at":"2026-06-05T01:14:59.323732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05687v1","created_at":"2026-06-05T01:14:59.323732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05687","created_at":"2026-06-05T01:14:59.323732+00:00"},{"alias_kind":"pith_short_12","alias_value":"COIVWEKU63CR","created_at":"2026-06-05T01:14:59.323732+00:00"},{"alias_kind":"pith_short_16","alias_value":"COIVWEKU63CRX6JJ","created_at":"2026-06-05T01:14:59.323732+00:00"},{"alias_kind":"pith_short_8","alias_value":"COIVWEKU","created_at":"2026-06-05T01:14:59.323732+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/COIVWEKU63CRX6JJR476DZHSLD","json":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD.json","graph_json":"https://pith.science/api/pith-number/COIVWEKU63CRX6JJR476DZHSLD/graph.json","events_json":"https://pith.science/api/pith-number/COIVWEKU63CRX6JJR476DZHSLD/events.json","paper":"https://pith.science/paper/COIVWEKU"},"agent_actions":{"view_html":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD","download_json":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD.json","view_paper":"https://pith.science/paper/COIVWEKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05687&json=true","fetch_graph":"https://pith.science/api/pith-number/COIVWEKU63CRX6JJR476DZHSLD/graph.json","fetch_events":"https://pith.science/api/pith-number/COIVWEKU63CRX6JJR476DZHSLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD/action/storage_attestation","attest_author":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD/action/author_attestation","sign_citation":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD/action/citation_signature","submit_replication":"https://pith.science/pith/COIVWEKU63CRX6JJR476DZHSLD/action/replication_record"}},"created_at":"2026-06-05T01:14:59.323732+00:00","updated_at":"2026-06-05T01:14:59.323732+00:00"}