{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UY335OKB2F6G5JVJKDDTQOOIZA","short_pith_number":"pith:UY335OKB","schema_version":"1.0","canonical_sha256":"a637beb941d17c6ea6a950c73839c8c8276f134699ed5cf95e8ce6a2cb636f0c","source":{"kind":"arxiv","id":"2011.02608","version":1},"attestation_state":"computed","paper":{"title":"Learning a Decentralized Multi-arm Motion Planner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Huy Ha, Jingxi Xu, Shuran Song","submitted_at":"2020-11-05T01:47:23Z","abstract_excerpt":"We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robot systems have relied on centralized motion planners, whose runtimes often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a decentralized policy is trained to control one robot arm in the multi-arm system to reach its target end-effector pose given observations of its workspace state and target end-effector pose. The policy is train"},"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":"2011.02608","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-05T01:47:23Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MA"],"title_canon_sha256":"65daa3550f73ce13b9a712f053c0a236153f77c06bc4080be0b424d368b3ad52","abstract_canon_sha256":"1fc165c367c21c695fdda609b0d245ef4af6806bca0a8f25311f5583ce2cca31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:23.169102Z","signature_b64":"JDX2JJaasiMzrZyCNLOJBEO5WkSx4E7MyCAeuDWdLKPVa0D/+H4oAm8wVCg1Qz5eOZ/K7RfKj/DJz/oJCJMbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a637beb941d17c6ea6a950c73839c8c8276f134699ed5cf95e8ce6a2cb636f0c","last_reissued_at":"2026-07-05T01:49:23.168720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:23.168720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning a Decentralized Multi-arm Motion Planner","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Huy Ha, Jingxi Xu, Shuran Song","submitted_at":"2020-11-05T01:47:23Z","abstract_excerpt":"We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robot systems have relied on centralized motion planners, whose runtimes often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a decentralized policy is trained to control one robot arm in the multi-arm system to reach its target end-effector pose given observations of its workspace state and target end-effector pose. The policy is train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02608","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/2011.02608/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":"2011.02608","created_at":"2026-07-05T01:49:23.168779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.02608v1","created_at":"2026-07-05T01:49:23.168779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02608","created_at":"2026-07-05T01:49:23.168779+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY335OKB2F6G","created_at":"2026-07-05T01:49:23.168779+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY335OKB2F6G5JVJ","created_at":"2026-07-05T01:49:23.168779+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY335OKB","created_at":"2026-07-05T01:49:23.168779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05397","citing_title":"RoboBallet: Planning for Multi-Robot Reaching with Graph Neural Networks and Reinforcement Learning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA","json":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA.json","graph_json":"https://pith.science/api/pith-number/UY335OKB2F6G5JVJKDDTQOOIZA/graph.json","events_json":"https://pith.science/api/pith-number/UY335OKB2F6G5JVJKDDTQOOIZA/events.json","paper":"https://pith.science/paper/UY335OKB"},"agent_actions":{"view_html":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA","download_json":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA.json","view_paper":"https://pith.science/paper/UY335OKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.02608&json=true","fetch_graph":"https://pith.science/api/pith-number/UY335OKB2F6G5JVJKDDTQOOIZA/graph.json","fetch_events":"https://pith.science/api/pith-number/UY335OKB2F6G5JVJKDDTQOOIZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA/action/storage_attestation","attest_author":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA/action/author_attestation","sign_citation":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA/action/citation_signature","submit_replication":"https://pith.science/pith/UY335OKB2F6G5JVJKDDTQOOIZA/action/replication_record"}},"created_at":"2026-07-05T01:49:23.168779+00:00","updated_at":"2026-07-05T01:49:23.168779+00:00"}