{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RLBURUTYGMVMLFGCDH4Q4EHVBX","short_pith_number":"pith:RLBURUTY","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"},"canonical_sha256":"8ac348d278332ac594c219f90e10f50de9aedc2c864d8e5073aa7884d9b5bbf3","source":{"kind":"arxiv","id":"2209.05738","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.05738","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"arxiv_version","alias_value":"2209.05738v2","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05738","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"pith_short_12","alias_value":"RLBURUTYGMVM","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"pith_short_16","alias_value":"RLBURUTYGMVMLFGC","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"pith_short_8","alias_value":"RLBURUTY","created_at":"2026-07-05T05:45:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RLBURUTYGMVMLFGCDH4Q4EHVBX","target":"record","payload":{"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"},"canonical_sha256":"8ac348d278332ac594c219f90e10f50de9aedc2c864d8e5073aa7884d9b5bbf3","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"},"source_kind":"arxiv","source_id":"2209.05738","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:45:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VADgYiz4Pjollp8wEuGJ9obwMkB34YjYsJqlwvg05vTKoOA4GmLwfNvLIKYKvkoVAbhK4d8f/THW4uRMxbocBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:14:27.263577Z"},"content_sha256":"15cfd9da9955ec06b55b4b33b66d4d4144cdc4e4548dc30b78f826e009ff5962","schema_version":"1.0","event_id":"sha256:15cfd9da9955ec06b55b4b33b66d4d4144cdc4e4548dc30b78f826e009ff5962"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RLBURUTYGMVMLFGCDH4Q4EHVBX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:45:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BF2V9SnTzftx8vykVNBul0muad5hFTexIYapov5mVoo5HiwVzOBtxfKoygZ6RjJqNbZ/NcgyA7imXezjlBaFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:14:27.264110Z"},"content_sha256":"9e074087410f088f10e59ecfd7f38eb799b7ceeeaf324c0c6ffb7d5e4b5c3624","schema_version":"1.0","event_id":"sha256:9e074087410f088f10e59ecfd7f38eb799b7ceeeaf324c0c6ffb7d5e4b5c3624"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/bundle.json","state_url":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T06:14:27Z","links":{"resolver":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX","bundle":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/bundle.json","state":"https://pith.science/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLBURUTYGMVMLFGCDH4Q4EHVBX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RLBURUTYGMVMLFGCDH4Q4EHVBX","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":"743254b7a9c1187c768f785a19dd6b9e8a83040053fd5e3af9f8ad27c3819ea3","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-13T05:21:53Z","title_canon_sha256":"93d90fd409b901eb13e6310e756222dcc1f9aad81cb27b2e6c57043260c69e16"},"schema_version":"1.0","source":{"id":"2209.05738","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.05738","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"arxiv_version","alias_value":"2209.05738v2","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.05738","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"pith_short_12","alias_value":"RLBURUTYGMVM","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"pith_short_16","alias_value":"RLBURUTYGMVMLFGC","created_at":"2026-07-05T05:45:32Z"},{"alias_kind":"pith_short_8","alias_value":"RLBURUTY","created_at":"2026-07-05T05:45:32Z"}],"graph_snapshots":[{"event_id":"sha256:9e074087410f088f10e59ecfd7f38eb799b7ceeeaf324c0c6ffb7d5e4b5c3624","target":"graph","created_at":"2026-07-05T05:45:32Z","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/2209.05738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aakriti Agrawal, Amrit Singh Bedi, Dinesh Manocha","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-13T05:21:53Z","title":"RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.05738","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":"sha256:15cfd9da9955ec06b55b4b33b66d4d4144cdc4e4548dc30b78f826e009ff5962","target":"record","created_at":"2026-07-05T05:45:32Z","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":"743254b7a9c1187c768f785a19dd6b9e8a83040053fd5e3af9f8ad27c3819ea3","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-09-13T05:21:53Z","title_canon_sha256":"93d90fd409b901eb13e6310e756222dcc1f9aad81cb27b2e6c57043260c69e16"},"schema_version":"1.0","source":{"id":"2209.05738","kind":"arxiv","version":2}},"canonical_sha256":"8ac348d278332ac594c219f90e10f50de9aedc2c864d8e5073aa7884d9b5bbf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ac348d278332ac594c219f90e10f50de9aedc2c864d8e5073aa7884d9b5bbf3","first_computed_at":"2026-07-05T05:45:32.819893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:32.819893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QtrUnyVSdXk+LCr1AXMgHt2yamLiy/MqyOMffRgo/mfEp7xF9q6U1veBiyrPOLkK3YkQwYKbhr4fLs3hbXAEDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:32.820456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.05738","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15cfd9da9955ec06b55b4b33b66d4d4144cdc4e4548dc30b78f826e009ff5962","sha256:9e074087410f088f10e59ecfd7f38eb799b7ceeeaf324c0c6ffb7d5e4b5c3624"],"state_sha256":"bfcb9d0598ad89fd59b6976bb84d95179a3d0f66c33822d336e19b5399681e00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KUxtwYBie3HRAktrVm3kReDuL5bReNRTXf80AM6nnE0zdK2WghpDFSJmMYxOgaxjGu1jhu3vWkzN7qlweVNPBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:14:27.270647Z","bundle_sha256":"81a1e8736c0ded39ba4ea859b5886e977e8d6f662456c2926ca6e23d72014006"}}