{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:75KAXS2PRX7W6H5LSZXQUN2LG7","short_pith_number":"pith:75KAXS2P","schema_version":"1.0","canonical_sha256":"ff540bcb4f8dff6f1fab966f0a374b37e18e3267879b71e803a1837513fa513c","source":{"kind":"arxiv","id":"2303.13539","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Awni Altabaa, Bora Yongacoglu, Serdar Y\\\"uksel","submitted_at":"2023-03-16T14:25:16Z","abstract_excerpt":"Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic games with general state spaces and an information structure in which agents do not observe each other's actions. In this context, we propose a decentralized MARL algorithm and we prove the near-optimality of its policy updates. Furthermore, we study the global policy-updating dynamics for a general class of best-reply based algorithms and derive a closed-form"},"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":"2303.13539","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T14:25:16Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"12afae21d870c4b8756763515b360426d8d6d626df360d521dbc0c488dcccfb2","abstract_canon_sha256":"7d8ef0ff6efbbd62c8df109caddbfd4c78ee7f14fa6bb7068040a26482150308"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:59.160799Z","signature_b64":"bjcCZQ0INii2ipBo0cnhxbYmloU2o6nHDMlHqp46gxIYlvaFkaz6KhFDBuo6PxGzp3dMRssnEzp5CkvCDoQoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff540bcb4f8dff6f1fab966f0a374b37e18e3267879b71e803a1837513fa513c","last_reissued_at":"2026-07-05T08:00:59.160332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:59.160332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Multi-Agent Reinforcement Learning for Continuous-Space Stochastic Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Awni Altabaa, Bora Yongacoglu, Serdar Y\\\"uksel","submitted_at":"2023-03-16T14:25:16Z","abstract_excerpt":"Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic games with general state spaces and an information structure in which agents do not observe each other's actions. In this context, we propose a decentralized MARL algorithm and we prove the near-optimality of its policy updates. Furthermore, we study the global policy-updating dynamics for a general class of best-reply based algorithms and derive a closed-form"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13539","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/2303.13539/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":"2303.13539","created_at":"2026-07-05T08:00:59.160390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13539v1","created_at":"2026-07-05T08:00:59.160390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13539","created_at":"2026-07-05T08:00:59.160390+00:00"},{"alias_kind":"pith_short_12","alias_value":"75KAXS2PRX7W","created_at":"2026-07-05T08:00:59.160390+00:00"},{"alias_kind":"pith_short_16","alias_value":"75KAXS2PRX7W6H5L","created_at":"2026-07-05T08:00:59.160390+00:00"},{"alias_kind":"pith_short_8","alias_value":"75KAXS2P","created_at":"2026-07-05T08:00:59.160390+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/75KAXS2PRX7W6H5LSZXQUN2LG7","json":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7.json","graph_json":"https://pith.science/api/pith-number/75KAXS2PRX7W6H5LSZXQUN2LG7/graph.json","events_json":"https://pith.science/api/pith-number/75KAXS2PRX7W6H5LSZXQUN2LG7/events.json","paper":"https://pith.science/paper/75KAXS2P"},"agent_actions":{"view_html":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7","download_json":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7.json","view_paper":"https://pith.science/paper/75KAXS2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13539&json=true","fetch_graph":"https://pith.science/api/pith-number/75KAXS2PRX7W6H5LSZXQUN2LG7/graph.json","fetch_events":"https://pith.science/api/pith-number/75KAXS2PRX7W6H5LSZXQUN2LG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/action/storage_attestation","attest_author":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/action/author_attestation","sign_citation":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/action/citation_signature","submit_replication":"https://pith.science/pith/75KAXS2PRX7W6H5LSZXQUN2LG7/action/replication_record"}},"created_at":"2026-07-05T08:00:59.160390+00:00","updated_at":"2026-07-05T08:00:59.160390+00:00"}