{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D7UULDNNVBM37T7VYQCMEWOBYG","short_pith_number":"pith:D7UULDNN","schema_version":"1.0","canonical_sha256":"1fe9458dada859bfcff5c404c259c1c195fbea64100b093e28dff12f50a41c96","source":{"kind":"arxiv","id":"2509.18371","version":2},"attestation_state":"computed","paper":{"title":"Policy Gradient with Self-Attention for Model-Free Distributed Nonlinear Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Carlos Sag\\\"u\\'es, Eduardo Montijano, Eduardo Sebasti\\'an, Eeman Iqbal, Maitrayee Keskar, Nikolay Atanasov","submitted_at":"2025-09-22T19:52:16Z","abstract_excerpt":"Multi-agent games in dynamic nonlinear settings are challenging due to the time-varying interactions among the agents and the non-stationarity of the (potential) Nash equilibria. In this paper we consider model-free games, where agent transitions and costs are observed without knowledge of the transition and cost functions that generate them. We propose a novel distributed policy structure that follows the communication constraints in multi-team games, with multiple agents per team, and learned through policy gradients. Our formulation is inspired by the structure of distributed policies in li"},"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":"2509.18371","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2025-09-22T19:52:16Z","cross_cats_sorted":["cs.MA","cs.RO","cs.SY"],"title_canon_sha256":"6b1cd587492ee3445bed9c9d122ae471920b3902c277268cd0d8ec9933f72b26","abstract_canon_sha256":"5a5112ed86ca97d4d380203cd02275c25b30199da21fb16ad66407cd8f8ae645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:58.521035Z","signature_b64":"r7x3G66fZI6bcfINdyW5IMb7iOW8yRlAL1a72rKDBlM0Sy6TwejAyC7BvybvgFm58rr6QAeP7v9cEomUDXQzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fe9458dada859bfcff5c404c259c1c195fbea64100b093e28dff12f50a41c96","last_reissued_at":"2026-06-24T01:14:58.520541Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:58.520541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient with Self-Attention for Model-Free Distributed Nonlinear Multi-Agent Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Carlos Sag\\\"u\\'es, Eduardo Montijano, Eduardo Sebasti\\'an, Eeman Iqbal, Maitrayee Keskar, Nikolay Atanasov","submitted_at":"2025-09-22T19:52:16Z","abstract_excerpt":"Multi-agent games in dynamic nonlinear settings are challenging due to the time-varying interactions among the agents and the non-stationarity of the (potential) Nash equilibria. In this paper we consider model-free games, where agent transitions and costs are observed without knowledge of the transition and cost functions that generate them. We propose a novel distributed policy structure that follows the communication constraints in multi-team games, with multiple agents per team, and learned through policy gradients. Our formulation is inspired by the structure of distributed policies in li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.18371","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/2509.18371/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":"2509.18371","created_at":"2026-06-24T01:14:58.520599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.18371v2","created_at":"2026-06-24T01:14:58.520599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.18371","created_at":"2026-06-24T01:14:58.520599+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7UULDNNVBM3","created_at":"2026-06-24T01:14:58.520599+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7UULDNNVBM37T7V","created_at":"2026-06-24T01:14:58.520599+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7UULDNN","created_at":"2026-06-24T01:14:58.520599+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/D7UULDNNVBM37T7VYQCMEWOBYG","json":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG.json","graph_json":"https://pith.science/api/pith-number/D7UULDNNVBM37T7VYQCMEWOBYG/graph.json","events_json":"https://pith.science/api/pith-number/D7UULDNNVBM37T7VYQCMEWOBYG/events.json","paper":"https://pith.science/paper/D7UULDNN"},"agent_actions":{"view_html":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG","download_json":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG.json","view_paper":"https://pith.science/paper/D7UULDNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.18371&json=true","fetch_graph":"https://pith.science/api/pith-number/D7UULDNNVBM37T7VYQCMEWOBYG/graph.json","fetch_events":"https://pith.science/api/pith-number/D7UULDNNVBM37T7VYQCMEWOBYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG/action/storage_attestation","attest_author":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG/action/author_attestation","sign_citation":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG/action/citation_signature","submit_replication":"https://pith.science/pith/D7UULDNNVBM37T7VYQCMEWOBYG/action/replication_record"}},"created_at":"2026-06-24T01:14:58.520599+00:00","updated_at":"2026-06-24T01:14:58.520599+00:00"}