{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CWTWR5LVC5LC2DIK56BO457X3S","short_pith_number":"pith:CWTWR5LV","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"},"canonical_sha256":"15a768f57517562d0d0aef82ee77f7dca486958d6dac6e2f0ced94ae3fc449e9","source":{"kind":"arxiv","id":"2011.14391","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14391","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14391v2","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14391","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"pith_short_12","alias_value":"CWTWR5LVC5LC","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"pith_short_16","alias_value":"CWTWR5LVC5LC2DIK","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"pith_short_8","alias_value":"CWTWR5LV","created_at":"2026-07-05T01:59:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CWTWR5LVC5LC2DIK56BO457X3S","target":"record","payload":{"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"},"canonical_sha256":"15a768f57517562d0d0aef82ee77f7dca486958d6dac6e2f0ced94ae3fc449e9","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"},"source_kind":"arxiv","source_id":"2011.14391","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:59:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXlpR/GweFgPUHzeBv5g/w0a6jTV3sevJ3JTP2bDYN33OyceQwPeNiomdDOBHqctwF5lDeukz1Bc5L5YrgUdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:51:37.591405Z"},"content_sha256":"85248a245426a43dbc99683b0d635a4871ff0a673d5b18a888401cb4316d4bbb","schema_version":"1.0","event_id":"sha256:85248a245426a43dbc99683b0d635a4871ff0a673d5b18a888401cb4316d4bbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CWTWR5LVC5LC2DIK56BO457X3S","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:59:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vOX29XZWgHCJGnw1qkLNjUeU8+GhrUfZxPejoTTlgWqMA2E2sNnqer00FlzR/Fo9Q3L4xI0gsfKe1/1gj8fwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:51:37.591938Z"},"content_sha256":"30434f3dbcdfe83a5ae8ddd29e629c9f35b283f3961299a60c9420b084e01123","schema_version":"1.0","event_id":"sha256:30434f3dbcdfe83a5ae8ddd29e629c9f35b283f3961299a60c9420b084e01123"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/bundle.json","state_url":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWTWR5LVC5LC2DIK56BO457X3S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T04:51:37Z","links":{"resolver":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S","bundle":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/bundle.json","state":"https://pith.science/pith/CWTWR5LVC5LC2DIK56BO457X3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWTWR5LVC5LC2DIK56BO457X3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CWTWR5LVC5LC2DIK56BO457X3S","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":"b6ff6df167e0eb9dbb0d4af5aaa836b3f5bff9a5bcbcfefe77a063f9dc5a66ea","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2020-11-29T15:53:21Z","title_canon_sha256":"7e32496e0c37db23a0ca2e587a5451727508847c863e9650b01de5ef3440d080"},"schema_version":"1.0","source":{"id":"2011.14391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14391","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14391v2","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14391","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"pith_short_12","alias_value":"CWTWR5LVC5LC","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"pith_short_16","alias_value":"CWTWR5LVC5LC2DIK","created_at":"2026-07-05T01:59:15Z"},{"alias_kind":"pith_short_8","alias_value":"CWTWR5LV","created_at":"2026-07-05T01:59:15Z"}],"graph_snapshots":[{"event_id":"sha256:30434f3dbcdfe83a5ae8ddd29e629c9f35b283f3961299a60c9420b084e01123","target":"graph","created_at":"2026-07-05T01:59:15Z","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/2011.14391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Amir G. Aghdam, Jalal Arabneydi, Masoud Roudneshin","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2020-11-29T15:53:21Z","title":"Reinforcement Learning in Nonzero-sum Linear Quadratic Deep Structured Games: Global Convergence of Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14391","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":"sha256:85248a245426a43dbc99683b0d635a4871ff0a673d5b18a888401cb4316d4bbb","target":"record","created_at":"2026-07-05T01:59:15Z","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":"b6ff6df167e0eb9dbb0d4af5aaa836b3f5bff9a5bcbcfefe77a063f9dc5a66ea","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2020-11-29T15:53:21Z","title_canon_sha256":"7e32496e0c37db23a0ca2e587a5451727508847c863e9650b01de5ef3440d080"},"schema_version":"1.0","source":{"id":"2011.14391","kind":"arxiv","version":2}},"canonical_sha256":"15a768f57517562d0d0aef82ee77f7dca486958d6dac6e2f0ced94ae3fc449e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15a768f57517562d0d0aef82ee77f7dca486958d6dac6e2f0ced94ae3fc449e9","first_computed_at":"2026-07-05T01:59:15.575078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:59:15.575078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YsjGvwdG0atyfvfNDEX8Md0UK2nAovH65pnKtcUfra8UkmXHseKEVjmZ0KeQYcW/1t3fEPq/iuHyVh22Xfq0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T01:59:15.575478Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.14391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85248a245426a43dbc99683b0d635a4871ff0a673d5b18a888401cb4316d4bbb","sha256:30434f3dbcdfe83a5ae8ddd29e629c9f35b283f3961299a60c9420b084e01123"],"state_sha256":"f0284f459d59585f291809e7fafd6e7e79b5e97c570a08a5b568c9d21524d245"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Im5aBtHYWs7tFBT+sxm9bNfqkoesw0C27MMDPfetKEAdxn6uqvx9hu7ZgOFAnD0mHenPeYe+Somk0lyRidnNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:51:37.595554Z","bundle_sha256":"7fa99d9e4ce2b5e80c5e5406b02c28185c2cf1dc477d1a6128d405832f7848e4"}}