{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RLBURUTYGMVMLFGCDH4Q4EHVBX","short_pith_number":"pith:RLBURUTY","schema_version":"1.0","canonical_sha256":"8ac348d278332ac594c219f90e10f50de9aedc2c864d8e5073aa7884d9b5bbf3","source":{"kind":"arxiv","id":"2209.05738","version":2},"attestation_state":"computed","paper":{"title":"RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Aakriti Agrawal, Amrit Singh Bedi, Dinesh Manocha","submitted_at":"2022-09-13T05:21:53Z","abstract_excerpt":"We present a novel reinforcement learning based algorithm for multi-robot task allocation problem in warehouse environments. We formulate it as a Markov Decision Process and solve via a novel deep multi-agent reinforcement learning method (called RTAW) with attention inspired policy architecture. Hence, our proposed policy network uses global embeddings that are independent of the number of robots/tasks. We utilize proximal policy optimization algorithm for training and use a carefully designed reward to obtain a converged policy. The converged policy ensures cooperation among different robots"},"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":"2209.05738","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-13T05:21:53Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"93d90fd409b901eb13e6310e756222dcc1f9aad81cb27b2e6c57043260c69e16","abstract_canon_sha256":"743254b7a9c1187c768f785a19dd6b9e8a83040053fd5e3af9f8ad27c3819ea3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:32.820456Z","signature_b64":"QtrUnyVSdXk+LCr1AXMgHt2yamLiy/MqyOMffRgo/mfEp7xF9q6U1veBiyrPOLkK3YkQwYKbhr4fLs3hbXAEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac348d278332ac594c219f90e10f50de9aedc2c864d8e5073aa7884d9b5bbf3","last_reissued_at":"2026-07-05T05:45:32.819893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:32.819893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Aakriti Agrawal, Amrit Singh Bedi, Dinesh Manocha","submitted_at":"2022-09-13T05:21:53Z","abstract_excerpt":"We present a novel reinforcement learning based algorithm for multi-robot task allocation problem in warehouse environments. We formulate it as a Markov Decision Process and solve via a novel deep multi-agent reinforcement learning method (called RTAW) with attention inspired policy architecture. Hence, our proposed policy network uses global embeddings that are independent of the number of robots/tasks. We utilize proximal policy optimization algorithm for training and use a carefully designed reward to obtain a converged policy. The converged policy ensures cooperation among different robots"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05738","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/2209.05738/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":"2209.05738","created_at":"2026-07-05T05:45:32.819970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.05738v2","created_at":"2026-07-05T05:45:32.819970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05738","created_at":"2026-07-05T05:45:32.819970+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLBURUTYGMVM","created_at":"2026-07-05T05:45:32.819970+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLBURUTYGMVMLFGC","created_at":"2026-07-05T05:45:32.819970+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLBURUTY","created_at":"2026-07-05T05:45:32.819970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.14063","citing_title":"Adaptive Obstacle-Aware Task Assignment and Planning for Heterogeneous Robot Teaming","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06557","citing_title":"Coordination Matters: Evaluation of Cooperative Multi-Agent Reinforcement Learning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX","json":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX.json","graph_json":"https://pith.science/api/pith-number/RLBURUTYGMVMLFGCDH4Q4EHVBX/graph.json","events_json":"https://pith.science/api/pith-number/RLBURUTYGMVMLFGCDH4Q4EHVBX/events.json","paper":"https://pith.science/paper/RLBURUTY"},"agent_actions":{"view_html":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX","download_json":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX.json","view_paper":"https://pith.science/paper/RLBURUTY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.05738&json=true","fetch_graph":"https://pith.science/api/pith-number/RLBURUTYGMVMLFGCDH4Q4EHVBX/graph.json","fetch_events":"https://pith.science/api/pith-number/RLBURUTYGMVMLFGCDH4Q4EHVBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/action/storage_attestation","attest_author":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/action/author_attestation","sign_citation":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/action/citation_signature","submit_replication":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/action/replication_record"}},"created_at":"2026-07-05T05:45:32.819970+00:00","updated_at":"2026-07-05T05:45:32.819970+00:00"}