{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LSZN4EWM4677FNU3BRJGFOQLVQ","short_pith_number":"pith:LSZN4EWM","schema_version":"1.0","canonical_sha256":"5cb2de12cce7bff2b69b0c5262ba0bac22cfc9a6fb8f1ca9006e60144b82dc58","source":{"kind":"arxiv","id":"2404.02362","version":1},"attestation_state":"computed","paper":{"title":"Task-priority Intermediated Hierarchical Distributed Policies: Reinforcement Learning of Adaptive Multi-robot Cooperative Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Tadashi Odashima, Takamitsu Matsubara, Tomohiko Jimbo, Yusei Naito","submitted_at":"2024-04-02T23:19:02Z","abstract_excerpt":"Multi-robot cooperative transport is crucial in logistics, housekeeping, and disaster response. However, it poses significant challenges in environments where objects of various weights are mixed and the number of robots and objects varies. This paper presents Task-priority Intermediated Hierarchical Distributed Policies (TIHDP), a multi-agent Reinforcement Learning (RL) framework that addresses these challenges through a hierarchical policy structure. TIHDP consists of three layers: task allocation policy (higher layer), dynamic task priority (intermediate layer), and robot control policy (lo"},"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":"2404.02362","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-04-02T23:19:02Z","cross_cats_sorted":[],"title_canon_sha256":"4aea558844a9450010aa697b5bb6bc909db184cccfe187c294f930218e6c5e59","abstract_canon_sha256":"687a2ecb2b400d100ee0fe14d58f5c32c97e3a18575057df8b9466624f5616e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:54.512681Z","signature_b64":"FMoaNXNZb0C5F5LLwek3gmwSqwyVpWdqldF18FCNuOFW1aR1K8P7XOatToq7P+xgggQoGPcQqCsiPATTUxJlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb2de12cce7bff2b69b0c5262ba0bac22cfc9a6fb8f1ca9006e60144b82dc58","last_reissued_at":"2026-07-05T08:03:54.512258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:54.512258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-priority Intermediated Hierarchical Distributed Policies: Reinforcement Learning of Adaptive Multi-robot Cooperative Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Tadashi Odashima, Takamitsu Matsubara, Tomohiko Jimbo, Yusei Naito","submitted_at":"2024-04-02T23:19:02Z","abstract_excerpt":"Multi-robot cooperative transport is crucial in logistics, housekeeping, and disaster response. However, it poses significant challenges in environments where objects of various weights are mixed and the number of robots and objects varies. This paper presents Task-priority Intermediated Hierarchical Distributed Policies (TIHDP), a multi-agent Reinforcement Learning (RL) framework that addresses these challenges through a hierarchical policy structure. TIHDP consists of three layers: task allocation policy (higher layer), dynamic task priority (intermediate layer), and robot control policy (lo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02362","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/2404.02362/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":"2404.02362","created_at":"2026-07-05T08:03:54.512324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02362v1","created_at":"2026-07-05T08:03:54.512324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02362","created_at":"2026-07-05T08:03:54.512324+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSZN4EWM4677","created_at":"2026-07-05T08:03:54.512324+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSZN4EWM4677FNU3","created_at":"2026-07-05T08:03:54.512324+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSZN4EWM","created_at":"2026-07-05T08:03:54.512324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11697","citing_title":"Rainbow Deep Q-Learning with Kinematics-Aware Design for Cooperative Delta and 3-RRS Parallel Robot Insertion","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ","json":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ.json","graph_json":"https://pith.science/api/pith-number/LSZN4EWM4677FNU3BRJGFOQLVQ/graph.json","events_json":"https://pith.science/api/pith-number/LSZN4EWM4677FNU3BRJGFOQLVQ/events.json","paper":"https://pith.science/paper/LSZN4EWM"},"agent_actions":{"view_html":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ","download_json":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ.json","view_paper":"https://pith.science/paper/LSZN4EWM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02362&json=true","fetch_graph":"https://pith.science/api/pith-number/LSZN4EWM4677FNU3BRJGFOQLVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LSZN4EWM4677FNU3BRJGFOQLVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ/action/storage_attestation","attest_author":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ/action/author_attestation","sign_citation":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ/action/citation_signature","submit_replication":"https://pith.science/pith/LSZN4EWM4677FNU3BRJGFOQLVQ/action/replication_record"}},"created_at":"2026-07-05T08:03:54.512324+00:00","updated_at":"2026-07-05T08:03:54.512324+00:00"}