{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CWTWR5LVC5LC2DIK56BO457X3S","short_pith_number":"pith:CWTWR5LV","schema_version":"1.0","canonical_sha256":"15a768f57517562d0d0aef82ee77f7dca486958d6dac6e2f0ced94ae3fc449e9","source":{"kind":"arxiv","id":"2011.14391","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning in Nonzero-sum Linear Quadratic Deep Structured Games: Global Convergence of Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.GT","authors_text":"Amir G. Aghdam, Jalal Arabneydi, Masoud Roudneshin","submitted_at":"2020-11-29T15:53:21Z","abstract_excerpt":"We study model-based and model-free policy optimization in a class of nonzero-sum stochastic dynamic games called linear quadratic (LQ) deep structured games. In such games, players interact with each other through a set of weighted averages (linear regressions) of the states and actions. In this paper, we focus our attention to homogeneous weights; however, for the special case of infinite population, the obtained results extend to asymptotically vanishing weights wherein the players learn the sequential weighted mean-field equilibrium. Despite the non-convexity of the optimization in policy "},"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":"2011.14391","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2020-11-29T15:53:21Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"7e32496e0c37db23a0ca2e587a5451727508847c863e9650b01de5ef3440d080","abstract_canon_sha256":"b6ff6df167e0eb9dbb0d4af5aaa836b3f5bff9a5bcbcfefe77a063f9dc5a66ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:59:15.575478Z","signature_b64":"YsjGvwdG0atyfvfNDEX8Md0UK2nAovH65pnKtcUfra8UkmXHseKEVjmZ0KeQYcW/1t3fEPq/iuHyVh22Xfq0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15a768f57517562d0d0aef82ee77f7dca486958d6dac6e2f0ced94ae3fc449e9","last_reissued_at":"2026-07-05T01:59:15.575078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:59:15.575078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning in Nonzero-sum Linear Quadratic Deep Structured Games: Global Convergence of Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.GT","authors_text":"Amir G. Aghdam, Jalal Arabneydi, Masoud Roudneshin","submitted_at":"2020-11-29T15:53:21Z","abstract_excerpt":"We study model-based and model-free policy optimization in a class of nonzero-sum stochastic dynamic games called linear quadratic (LQ) deep structured games. In such games, players interact with each other through a set of weighted averages (linear regressions) of the states and actions. In this paper, we focus our attention to homogeneous weights; however, for the special case of infinite population, the obtained results extend to asymptotically vanishing weights wherein the players learn the sequential weighted mean-field equilibrium. Despite the non-convexity of the optimization in policy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14391","kind":"arxiv","version":2},"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/2011.14391/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":"2011.14391","created_at":"2026-07-05T01:59:15.575132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14391v2","created_at":"2026-07-05T01:59:15.575132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14391","created_at":"2026-07-05T01:59:15.575132+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWTWR5LVC5LC","created_at":"2026-07-05T01:59:15.575132+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWTWR5LVC5LC2DIK","created_at":"2026-07-05T01:59:15.575132+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWTWR5LV","created_at":"2026-07-05T01:59:15.575132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20675","citing_title":"Bridging Finite and Infinite-Horizon Nash Equilibria in Linear Quadratic Games","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S","json":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S.json","graph_json":"https://pith.science/api/pith-number/CWTWR5LVC5LC2DIK56BO457X3S/graph.json","events_json":"https://pith.science/api/pith-number/CWTWR5LVC5LC2DIK56BO457X3S/events.json","paper":"https://pith.science/paper/CWTWR5LV"},"agent_actions":{"view_html":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S","download_json":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S.json","view_paper":"https://pith.science/paper/CWTWR5LV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14391&json=true","fetch_graph":"https://pith.science/api/pith-number/CWTWR5LVC5LC2DIK56BO457X3S/graph.json","fetch_events":"https://pith.science/api/pith-number/CWTWR5LVC5LC2DIK56BO457X3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/action/storage_attestation","attest_author":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/action/author_attestation","sign_citation":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/action/citation_signature","submit_replication":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/action/replication_record"}},"created_at":"2026-07-05T01:59:15.575132+00:00","updated_at":"2026-07-05T01:59:15.575132+00:00"}