{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OOFKDM56NTSAACVDFOYQXDZEJS","short_pith_number":"pith:OOFKDM56","schema_version":"1.0","canonical_sha256":"738aa1b3be6ce4000aa32bb10b8f244c9a67e932e06cec24e9e1769debb0b524","source":{"kind":"arxiv","id":"1908.05224","version":2},"attestation_state":"computed","paper":{"title":"Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hugo Ponte, Michael Ahn, Ofir Nachum, Shixiang Gu, Vikash Kumar","submitted_at":"2019-08-13T15:12:02Z","abstract_excerpt":"Manipulation and locomotion are closely related problems that are often studied in isolation. In this work, we study the problem of coordinating multiple mobile agents to exhibit manipulation behaviors using a reinforcement learning (RL) approach. Our method hinges on the use of hierarchical sim2real -- a simulated environment is used to learn low-level goal-reaching skills, which are then used as the action space for a high-level RL controller, also trained in simulation. The full hierarchical policy is then transferred to the real world in a zero-shot fashion. The application of domain rando"},"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":"1908.05224","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-13T15:12:02Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a5783c45b58df9441de1c15f1b8369552198eaff665622f1c7bd6518741913d7","abstract_canon_sha256":"0b84e3d446652aa0c2a677f37f67f6f014cc106d9c9e7e606ef988e164972944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:15.652326Z","signature_b64":"H6TbYRMGUsypk6l5MLDsI1FzNuQCrabGgjxEoiRhb1aDbsmxgbfQl1yL5sot6F94roAqvAQNvOTKOpEUazuUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"738aa1b3be6ce4000aa32bb10b8f244c9a67e932e06cec24e9e1769debb0b524","last_reissued_at":"2026-07-05T00:10:15.651787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:15.651787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Hugo Ponte, Michael Ahn, Ofir Nachum, Shixiang Gu, Vikash Kumar","submitted_at":"2019-08-13T15:12:02Z","abstract_excerpt":"Manipulation and locomotion are closely related problems that are often studied in isolation. In this work, we study the problem of coordinating multiple mobile agents to exhibit manipulation behaviors using a reinforcement learning (RL) approach. Our method hinges on the use of hierarchical sim2real -- a simulated environment is used to learn low-level goal-reaching skills, which are then used as the action space for a high-level RL controller, also trained in simulation. The full hierarchical policy is then transferred to the real world in a zero-shot fashion. The application of domain rando"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05224","kind":"arxiv","version":2},"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/1908.05224/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":"1908.05224","created_at":"2026-07-05T00:10:15.651862+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05224v2","created_at":"2026-07-05T00:10:15.651862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05224","created_at":"2026-07-05T00:10:15.651862+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOFKDM56NTSA","created_at":"2026-07-05T00:10:15.651862+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOFKDM56NTSAACVD","created_at":"2026-07-05T00:10:15.651862+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOFKDM56","created_at":"2026-07-05T00:10:15.651862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29358","citing_title":"LAMP: Long-Horizon Adaptive Manipulation Planning for Multi-Robot Collaboration in Cluttered Space","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15289","citing_title":"Abstract Sim2Real through Approximate Information States","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS","json":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS.json","graph_json":"https://pith.science/api/pith-number/OOFKDM56NTSAACVDFOYQXDZEJS/graph.json","events_json":"https://pith.science/api/pith-number/OOFKDM56NTSAACVDFOYQXDZEJS/events.json","paper":"https://pith.science/paper/OOFKDM56"},"agent_actions":{"view_html":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS","download_json":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS.json","view_paper":"https://pith.science/paper/OOFKDM56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05224&json=true","fetch_graph":"https://pith.science/api/pith-number/OOFKDM56NTSAACVDFOYQXDZEJS/graph.json","fetch_events":"https://pith.science/api/pith-number/OOFKDM56NTSAACVDFOYQXDZEJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS/action/storage_attestation","attest_author":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS/action/author_attestation","sign_citation":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS/action/citation_signature","submit_replication":"https://pith.science/pith/OOFKDM56NTSAACVDFOYQXDZEJS/action/replication_record"}},"created_at":"2026-07-05T00:10:15.651862+00:00","updated_at":"2026-07-05T00:10:15.651862+00:00"}