{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DBN7VXNNCGKASACES7HMY2MKBK","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":"4112459b3bf2f6ae2c6a395d2c9f8d22eb644aa8f771cfc7605e2b8f6c9d39cd","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2020-11-29T16:02:39Z","title_canon_sha256":"810ec781b8e031d86f5dbe4c9d670c0dddf394dd82815ef1dbbf6212487beb35"},"schema_version":"1.0","source":{"id":"2011.14393","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14393","created_at":"2026-07-05T01:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14393v2","created_at":"2026-07-05T01:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14393","created_at":"2026-07-05T01:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"DBN7VXNNCGKA","created_at":"2026-07-05T01:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"DBN7VXNNCGKASACE","created_at":"2026-07-05T01:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"DBN7VXNN","created_at":"2026-07-05T01:59:35Z"}],"graph_snapshots":[{"event_id":"sha256:9187fc4bbb54b25dd2ece6b3506723820f47e61fa10398023fd3c4a303eeca81","target":"graph","created_at":"2026-07-05T01:59:35Z","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/2011.14393/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the global convergence of model-based and model-free policy gradient descent and natural policy gradient descent algorithms for linear quadratic deep structured teams. In such systems, agents are partitioned into a few sub-populations wherein the agents in each sub-population are coupled in the dynamics and cost function through a set of linear regressions of the states and actions of all agents. Every agent observes its local state and the linear regressions of states, called deep states. For a sufficiently small risk factor and/or sufficiently large population, we pro","authors_text":"Amir G. Aghdam, Jalal Arabneydi, Vida Fathi","cross_cats":["cs.LG","cs.SY","eess.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2020-11-29T16:02:39Z","title":"Reinforcement Learning in Linear Quadratic Deep Structured Teams: Global Convergence of Policy Gradient Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14393","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:fe65294a23217590a9e4e85ef14339874abbdb6f34834d95f17ed506cdc2f290","target":"record","created_at":"2026-07-05T01:59:35Z","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":"4112459b3bf2f6ae2c6a395d2c9f8d22eb644aa8f771cfc7605e2b8f6c9d39cd","cross_cats_sorted":["cs.LG","cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2020-11-29T16:02:39Z","title_canon_sha256":"810ec781b8e031d86f5dbe4c9d670c0dddf394dd82815ef1dbbf6212487beb35"},"schema_version":"1.0","source":{"id":"2011.14393","kind":"arxiv","version":2}},"canonical_sha256":"185bfaddad119409004497cecc698a0abd1c8c9dceaf24974da7574c656d8c24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"185bfaddad119409004497cecc698a0abd1c8c9dceaf24974da7574c656d8c24","first_computed_at":"2026-07-05T01:59:35.466995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:35.466995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ITvuMqNNidMwW56Si7BOkzZQ6mzYiIIanWQ/Rx1bITqWxf8/5S37auiNTzQvIwfphLqGd6Qq47EMp7UYIr49Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:35.467483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.14393","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe65294a23217590a9e4e85ef14339874abbdb6f34834d95f17ed506cdc2f290","sha256:9187fc4bbb54b25dd2ece6b3506723820f47e61fa10398023fd3c4a303eeca81"],"state_sha256":"8831a7d578aeec6b0776b0e14b54ed4e3abee43b9ca70a3a47e17a74f36e37ef"}