{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OOFKDM56NTSAACVDFOYQXDZEJS","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":"0b84e3d446652aa0c2a677f37f67f6f014cc106d9c9e7e606ef988e164972944","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-13T15:12:02Z","title_canon_sha256":"a5783c45b58df9441de1c15f1b8369552198eaff665622f1c7bd6518741913d7"},"schema_version":"1.0","source":{"id":"1908.05224","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.05224","created_at":"2026-07-05T00:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"1908.05224v2","created_at":"2026-07-05T00:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05224","created_at":"2026-07-05T00:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"OOFKDM56NTSA","created_at":"2026-07-05T00:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"OOFKDM56NTSAACVD","created_at":"2026-07-05T00:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"OOFKDM56","created_at":"2026-07-05T00:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:c347d82df08b381b46abfd32c7e82cf094d28f05d03954f7a68a516a82691d25","target":"graph","created_at":"2026-07-05T00:10:15Z","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/1908.05224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hugo Ponte, Michael Ahn, Ofir Nachum, Shixiang Gu, Vikash Kumar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-13T15:12:02Z","title":"Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05224","kind":"arxiv","version":2},"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":"sha256:20ea7482d9a38011823a2f6997ff39513de5d003beedae148b122b2ec7c16401","target":"record","created_at":"2026-07-05T00:10:15Z","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":"0b84e3d446652aa0c2a677f37f67f6f014cc106d9c9e7e606ef988e164972944","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-08-13T15:12:02Z","title_canon_sha256":"a5783c45b58df9441de1c15f1b8369552198eaff665622f1c7bd6518741913d7"},"schema_version":"1.0","source":{"id":"1908.05224","kind":"arxiv","version":2}},"canonical_sha256":"738aa1b3be6ce4000aa32bb10b8f244c9a67e932e06cec24e9e1769debb0b524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"738aa1b3be6ce4000aa32bb10b8f244c9a67e932e06cec24e9e1769debb0b524","first_computed_at":"2026-07-05T00:10:15.651787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:15.651787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H6TbYRMGUsypk6l5MLDsI1FzNuQCrabGgjxEoiRhb1aDbsmxgbfQl1yL5sot6F94roAqvAQNvOTKOpEUazuUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:15.652326Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.05224","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20ea7482d9a38011823a2f6997ff39513de5d003beedae148b122b2ec7c16401","sha256:c347d82df08b381b46abfd32c7e82cf094d28f05d03954f7a68a516a82691d25"],"state_sha256":"902789029afc6fcf8f21eeadb3cb51f00fa8fac4d48da4a5f4660131151ef6e7"}