{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6TOAYSIM3D5JOAI5K6TWAPCT3B","short_pith_number":"pith:6TOAYSIM","schema_version":"1.0","canonical_sha256":"f4dc0c490cd8fa97011d57a7603c53d86e71db605916766449e814d0bf901e15","source":{"kind":"arxiv","id":"2305.00684","version":1},"attestation_state":"computed","paper":{"title":"On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dean P. Foster, Dylan J. Foster, Noah Golowich","submitted_at":"2023-05-01T06:46:22Z","abstract_excerpt":"A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move from few to many agents. We study this question in a general framework for interactive decision making with multiple agents, encompassing Markov games with function approximation and normal-form games with bandit feedback. We focus on equilibrium computation, in which a centralized learning algorithm aims to compute an equilibrium by controlling multiple ag"},"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":"2305.00684","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-01T06:46:22Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","stat.ML"],"title_canon_sha256":"66e6d0234ca46c2bde30c267a2d7261d26091c974a88819d7288fac88760039d","abstract_canon_sha256":"e6c51bfeb5866b98ccc17e11d407bd9b3e6c9301c90c8bf91c0e5be0faffcafa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:44.063997Z","signature_b64":"YlM1BfNkNStUA3gvBhS5lzPCd2sbjQHwsCnTCTlLLS46Sy2KTx/NfkLUY49KSAhN6G9sBT0YQVqufKdz1RmaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4dc0c490cd8fa97011d57a7603c53d86e71db605916766449e814d0bf901e15","last_reissued_at":"2026-07-05T06:05:44.063677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:44.063677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dean P. Foster, Dylan J. Foster, Noah Golowich","submitted_at":"2023-05-01T06:46:22Z","abstract_excerpt":"A central problem in the theory of multi-agent reinforcement learning (MARL) is to understand what structural conditions and algorithmic principles lead to sample-efficient learning guarantees, and how these considerations change as we move from few to many agents. We study this question in a general framework for interactive decision making with multiple agents, encompassing Markov games with function approximation and normal-form games with bandit feedback. We focus on equilibrium computation, in which a centralized learning algorithm aims to compute an equilibrium by controlling multiple ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00684","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/2305.00684/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":"2305.00684","created_at":"2026-07-05T06:05:44.063728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00684v1","created_at":"2026-07-05T06:05:44.063728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00684","created_at":"2026-07-05T06:05:44.063728+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TOAYSIM3D5J","created_at":"2026-07-05T06:05:44.063728+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TOAYSIM3D5JOAI5","created_at":"2026-07-05T06:05:44.063728+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TOAYSIM","created_at":"2026-07-05T06:05:44.063728+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/6TOAYSIM3D5JOAI5K6TWAPCT3B","json":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B.json","graph_json":"https://pith.science/api/pith-number/6TOAYSIM3D5JOAI5K6TWAPCT3B/graph.json","events_json":"https://pith.science/api/pith-number/6TOAYSIM3D5JOAI5K6TWAPCT3B/events.json","paper":"https://pith.science/paper/6TOAYSIM"},"agent_actions":{"view_html":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B","download_json":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B.json","view_paper":"https://pith.science/paper/6TOAYSIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00684&json=true","fetch_graph":"https://pith.science/api/pith-number/6TOAYSIM3D5JOAI5K6TWAPCT3B/graph.json","fetch_events":"https://pith.science/api/pith-number/6TOAYSIM3D5JOAI5K6TWAPCT3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B/action/storage_attestation","attest_author":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B/action/author_attestation","sign_citation":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B/action/citation_signature","submit_replication":"https://pith.science/pith/6TOAYSIM3D5JOAI5K6TWAPCT3B/action/replication_record"}},"created_at":"2026-07-05T06:05:44.063728+00:00","updated_at":"2026-07-05T06:05:44.063728+00:00"}