{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:PGGMDDOCG5ND2B4YCCLRYUVFRA","short_pith_number":"pith:PGGMDDOC","schema_version":"1.0","canonical_sha256":"798cc18dc2375a3d079810971c52a5880639254310354025b6cd6e79237aea4b","source":{"kind":"arxiv","id":"2204.03516","version":1},"attestation_state":"computed","paper":{"title":"Distributed Reinforcement Learning for Robot Teams: A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Guillaume Sartoretti, Mehul Damani, Pamela Wang, Yuhong Cao, Yutong Wang","submitted_at":"2022-04-07T15:34:19Z","abstract_excerpt":"Purpose of review: Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems consisting of hundreds/thousands of robots, with promising applications to automated manufacturing, disaster relief, harvesting, last-mile delivery, port/airport operations, or search and rescue. The community has leveraged model-free multi-agent reinforcement learning (MARL) to devise efficient, scalable controllers for multi-robot systems (MRS). This review aims to provide an analysis of the state-of-the-art in distributed MARL for multi-robot cooperation.\n  Recent findings: "},"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":"2204.03516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-04-07T15:34:19Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"5127b61d56eb53342c99cfaf69c131a67b419feeb26abcd987cda31cc0a5d4a7","abstract_canon_sha256":"8ce46e08d25effcc4e14c7fafb358b8575e2ca420b5cf74751630815c79688ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:12:31.113142Z","signature_b64":"HWV4lAO6jISSdnAfw8WagSNlg9JBEZT/NDfNJli8n/mqYdRhnALrEWt3YffW7ZRd7aXybcAPsDsniPx+DlNBDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"798cc18dc2375a3d079810971c52a5880639254310354025b6cd6e79237aea4b","last_reissued_at":"2026-07-05T04:12:31.112698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:12:31.112698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Reinforcement Learning for Robot Teams: A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.RO","authors_text":"Guillaume Sartoretti, Mehul Damani, Pamela Wang, Yuhong Cao, Yutong Wang","submitted_at":"2022-04-07T15:34:19Z","abstract_excerpt":"Purpose of review: Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems consisting of hundreds/thousands of robots, with promising applications to automated manufacturing, disaster relief, harvesting, last-mile delivery, port/airport operations, or search and rescue. The community has leveraged model-free multi-agent reinforcement learning (MARL) to devise efficient, scalable controllers for multi-robot systems (MRS). This review aims to provide an analysis of the state-of-the-art in distributed MARL for multi-robot cooperation.\n  Recent findings: "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03516","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/2204.03516/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":"2204.03516","created_at":"2026-07-05T04:12:31.112754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03516v1","created_at":"2026-07-05T04:12:31.112754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03516","created_at":"2026-07-05T04:12:31.112754+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGGMDDOCG5ND","created_at":"2026-07-05T04:12:31.112754+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGGMDDOCG5ND2B4Y","created_at":"2026-07-05T04:12:31.112754+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGGMDDOC","created_at":"2026-07-05T04:12:31.112754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12326","citing_title":"Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharing","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA","json":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA.json","graph_json":"https://pith.science/api/pith-number/PGGMDDOCG5ND2B4YCCLRYUVFRA/graph.json","events_json":"https://pith.science/api/pith-number/PGGMDDOCG5ND2B4YCCLRYUVFRA/events.json","paper":"https://pith.science/paper/PGGMDDOC"},"agent_actions":{"view_html":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA","download_json":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA.json","view_paper":"https://pith.science/paper/PGGMDDOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03516&json=true","fetch_graph":"https://pith.science/api/pith-number/PGGMDDOCG5ND2B4YCCLRYUVFRA/graph.json","fetch_events":"https://pith.science/api/pith-number/PGGMDDOCG5ND2B4YCCLRYUVFRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA/action/storage_attestation","attest_author":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA/action/author_attestation","sign_citation":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA/action/citation_signature","submit_replication":"https://pith.science/pith/PGGMDDOCG5ND2B4YCCLRYUVFRA/action/replication_record"}},"created_at":"2026-07-05T04:12:31.112754+00:00","updated_at":"2026-07-05T04:12:31.112754+00:00"}