{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NQ2WAUY4CF2YYZ5B32TIWDIJZH","short_pith_number":"pith:NQ2WAUY4","schema_version":"1.0","canonical_sha256":"6c3560531c11758c67a1dea68b0d09c9e7f09b85004121dd120ef8b3877fdb4d","source":{"kind":"arxiv","id":"2001.10122","version":1},"attestation_state":"computed","paper":{"title":"Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashutosh Nayyar, Seyed Mohammad Asghari, Yi Ouyang","submitted_at":"2020-01-27T23:37:41Z","abstract_excerpt":"Regret analysis is challenging in Multi-Agent Reinforcement Learning (MARL) primarily due to the dynamical environments and the decentralized information among agents. We attempt to solve this challenge in the context of decentralized learning in multi-agent linear-quadratic (LQ) dynamical systems. We begin with a simple setup consisting of two agents and two dynamically decoupled stochastic linear systems, each system controlled by an agent. The systems are coupled through a quadratic cost function. When both systems' dynamics are unknown and there is no communication among the agents, we sho"},"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":"2001.10122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-27T23:37:41Z","cross_cats_sorted":["cs.MA","math.OC","stat.ML"],"title_canon_sha256":"419827408279cb59e4c8dd0fdd5a9c44f045d1e1bf8fe8ce26e162b20391932d","abstract_canon_sha256":"4f11fee009b16e9b207ec163e394acb67d90bd3903be95dde69f57482f1087fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:36:49.965249Z","signature_b64":"r3/RC37+zF5hiCk9zv4sYsN0PM4tDSZyPyZpZo5vXRLaM9BYueSZtNZ9eXSWSNz1OV1K+u4wac8BJHw61KVzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c3560531c11758c67a1dea68b0d09c9e7f09b85004121dd120ef8b3877fdb4d","last_reissued_at":"2026-07-05T00:36:49.964839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:36:49.964839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ashutosh Nayyar, Seyed Mohammad Asghari, Yi Ouyang","submitted_at":"2020-01-27T23:37:41Z","abstract_excerpt":"Regret analysis is challenging in Multi-Agent Reinforcement Learning (MARL) primarily due to the dynamical environments and the decentralized information among agents. We attempt to solve this challenge in the context of decentralized learning in multi-agent linear-quadratic (LQ) dynamical systems. We begin with a simple setup consisting of two agents and two dynamically decoupled stochastic linear systems, each system controlled by an agent. The systems are coupled through a quadratic cost function. When both systems' dynamics are unknown and there is no communication among the agents, we sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.10122","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/2001.10122/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":"2001.10122","created_at":"2026-07-05T00:36:49.964902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.10122v1","created_at":"2026-07-05T00:36:49.964902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.10122","created_at":"2026-07-05T00:36:49.964902+00:00"},{"alias_kind":"pith_short_12","alias_value":"NQ2WAUY4CF2Y","created_at":"2026-07-05T00:36:49.964902+00:00"},{"alias_kind":"pith_short_16","alias_value":"NQ2WAUY4CF2YYZ5B","created_at":"2026-07-05T00:36:49.964902+00:00"},{"alias_kind":"pith_short_8","alias_value":"NQ2WAUY4","created_at":"2026-07-05T00:36:49.964902+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/NQ2WAUY4CF2YYZ5B32TIWDIJZH","json":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH.json","graph_json":"https://pith.science/api/pith-number/NQ2WAUY4CF2YYZ5B32TIWDIJZH/graph.json","events_json":"https://pith.science/api/pith-number/NQ2WAUY4CF2YYZ5B32TIWDIJZH/events.json","paper":"https://pith.science/paper/NQ2WAUY4"},"agent_actions":{"view_html":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH","download_json":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH.json","view_paper":"https://pith.science/paper/NQ2WAUY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.10122&json=true","fetch_graph":"https://pith.science/api/pith-number/NQ2WAUY4CF2YYZ5B32TIWDIJZH/graph.json","fetch_events":"https://pith.science/api/pith-number/NQ2WAUY4CF2YYZ5B32TIWDIJZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH/action/storage_attestation","attest_author":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH/action/author_attestation","sign_citation":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH/action/citation_signature","submit_replication":"https://pith.science/pith/NQ2WAUY4CF2YYZ5B32TIWDIJZH/action/replication_record"}},"created_at":"2026-07-05T00:36:49.964902+00:00","updated_at":"2026-07-05T00:36:49.964902+00:00"}