{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DWTVGMUF45KBY75O5MTMESEONR","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":"50cf64764ddbcdd1ad2734e5c6c3ac4156a1c7d3e13e979acc8b413a1cc543ee","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2023-12-08T16:47:09Z","title_canon_sha256":"d132b757ed0e11bb9227bf852191a055d6b5b5900234c7bd926964497a4c2ab7"},"schema_version":"1.0","source":{"id":"2312.05166","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05166","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05166v4","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05166","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_12","alias_value":"DWTVGMUF45KB","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_16","alias_value":"DWTVGMUF45KBY75O","created_at":"2026-07-05T09:56:20Z"},{"alias_kind":"pith_short_8","alias_value":"DWTVGMUF","created_at":"2026-07-05T09:56:20Z"}],"graph_snapshots":[{"event_id":"sha256:67c6261695c4c14e529a4df0240fa1a5357009bfcdfe581ab33acbfaef93514d","target":"graph","created_at":"2026-07-05T09:56:20Z","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/2312.05166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Azita Dabiri, Bart De Schutter, Filippo Airaldi, Samuel Mallick","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2023-12-08T16:47:09Z","title":"Multi-Agent Reinforcement Learning via Distributed MPC as a Function Approximator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05166","kind":"arxiv","version":4},"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:f5a8a6188046b68fcc5676d6f0afadb5bdbfc69c8d06251fd275e81343fdd93d","target":"record","created_at":"2026-07-05T09:56:20Z","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":"50cf64764ddbcdd1ad2734e5c6c3ac4156a1c7d3e13e979acc8b413a1cc543ee","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2023-12-08T16:47:09Z","title_canon_sha256":"d132b757ed0e11bb9227bf852191a055d6b5b5900234c7bd926964497a4c2ab7"},"schema_version":"1.0","source":{"id":"2312.05166","kind":"arxiv","version":4}},"canonical_sha256":"1da7533285e7541c7faeeb26c2488e6c73315eb98d7f0ee0cfdf6c84722a8abd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1da7533285e7541c7faeeb26c2488e6c73315eb98d7f0ee0cfdf6c84722a8abd","first_computed_at":"2026-07-05T09:56:20.479728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:20.479728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EFGHBrts5CdMpsnUiOJVBGm1Aym5sgkNptS6i0yZpDW0BYbMpQsR9495Di2hbCaw9gtJuvJt/XOi587yWfPhBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:20.480151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.05166","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5a8a6188046b68fcc5676d6f0afadb5bdbfc69c8d06251fd275e81343fdd93d","sha256:67c6261695c4c14e529a4df0240fa1a5357009bfcdfe581ab33acbfaef93514d"],"state_sha256":"af3cce6ae426938b98eca5da42fda0fdb842912bf38a414ce3ded5c92f5c827d"}