{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DWTVGMUF45KBY75O5MTMESEONR","short_pith_number":"pith:DWTVGMUF","schema_version":"1.0","canonical_sha256":"1da7533285e7541c7faeeb26c2488e6c73315eb98d7f0ee0cfdf6c84722a8abd","source":{"kind":"arxiv","id":"2312.05166","version":4},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning via Distributed MPC as a Function Approximator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Azita Dabiri, Bart De Schutter, Filippo Airaldi, Samuel Mallick","submitted_at":"2023-12-08T16:47:09Z","abstract_excerpt":"This paper presents a novel approach to multi-agent reinforcement learning (RL) for linear systems with convex polytopic constraints. Existing work on RL has demonstrated the use of model predictive control (MPC) as a function approximator for the policy and value functions. The current paper is the first work to extend this idea to the multi-agent setting. We propose the use of a distributed MPC scheme as a function approximator, with a structure allowing for distributed learning and deployment. We then show that Q-learning updates can be performed distributively without introducing nonstatio"},"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":"2312.05166","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2023-12-08T16:47:09Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"d132b757ed0e11bb9227bf852191a055d6b5b5900234c7bd926964497a4c2ab7","abstract_canon_sha256":"50cf64764ddbcdd1ad2734e5c6c3ac4156a1c7d3e13e979acc8b413a1cc543ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:20.480151Z","signature_b64":"EFGHBrts5CdMpsnUiOJVBGm1Aym5sgkNptS6i0yZpDW0BYbMpQsR9495Di2hbCaw9gtJuvJt/XOi587yWfPhBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1da7533285e7541c7faeeb26c2488e6c73315eb98d7f0ee0cfdf6c84722a8abd","last_reissued_at":"2026-07-05T09:56:20.479728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:20.479728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning via Distributed MPC as a Function Approximator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Azita Dabiri, Bart De Schutter, Filippo Airaldi, Samuel Mallick","submitted_at":"2023-12-08T16:47:09Z","abstract_excerpt":"This paper presents a novel approach to multi-agent reinforcement learning (RL) for linear systems with convex polytopic constraints. Existing work on RL has demonstrated the use of model predictive control (MPC) as a function approximator for the policy and value functions. The current paper is the first work to extend this idea to the multi-agent setting. We propose the use of a distributed MPC scheme as a function approximator, with a structure allowing for distributed learning and deployment. We then show that Q-learning updates can be performed distributively without introducing nonstatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05166","kind":"arxiv","version":4},"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/2312.05166/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":"2312.05166","created_at":"2026-07-05T09:56:20.479781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05166v4","created_at":"2026-07-05T09:56:20.479781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05166","created_at":"2026-07-05T09:56:20.479781+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWTVGMUF45KB","created_at":"2026-07-05T09:56:20.479781+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWTVGMUF45KBY75O","created_at":"2026-07-05T09:56:20.479781+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWTVGMUF","created_at":"2026-07-05T09:56:20.479781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR","json":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR.json","graph_json":"https://pith.science/api/pith-number/DWTVGMUF45KBY75O5MTMESEONR/graph.json","events_json":"https://pith.science/api/pith-number/DWTVGMUF45KBY75O5MTMESEONR/events.json","paper":"https://pith.science/paper/DWTVGMUF"},"agent_actions":{"view_html":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR","download_json":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR.json","view_paper":"https://pith.science/paper/DWTVGMUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05166&json=true","fetch_graph":"https://pith.science/api/pith-number/DWTVGMUF45KBY75O5MTMESEONR/graph.json","fetch_events":"https://pith.science/api/pith-number/DWTVGMUF45KBY75O5MTMESEONR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR/action/storage_attestation","attest_author":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR/action/author_attestation","sign_citation":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR/action/citation_signature","submit_replication":"https://pith.science/pith/DWTVGMUF45KBY75O5MTMESEONR/action/replication_record"}},"created_at":"2026-07-05T09:56:20.479781+00:00","updated_at":"2026-07-05T09:56:20.479781+00:00"}