{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GOJOUDPS5KI7LMQODCLMJO3BIG","short_pith_number":"pith:GOJOUDPS","schema_version":"1.0","canonical_sha256":"3392ea0df2ea91f5b20e1896c4bb6141bfad1b87d0ce988bb47d797e29659ee3","source":{"kind":"arxiv","id":"2608.12753","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"King Bi, Larissa Xu, William Chang","submitted_at":"2026-08-13T03:06:11Z","abstract_excerpt":"We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards. Players cannot communicate during learning but may agree on a protocol a priori. For Problems A and B we propose \\texttt{mQ-learning} and \\texttt{mQ-learning-intervals}, achieving $\\tilde{O}(\\sqrt{H^4 S A_{\\text{joint}}\\, T})$ regret, where $H$ is the horizon, $S$ the state count, $T = KH$ the total"},"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":"2608.12753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T03:06:11Z","cross_cats_sorted":[],"title_canon_sha256":"1d534f48bf875467bc9db317c438a3d6693c12fddd36c5a1508a7ac5b6e89ebe","abstract_canon_sha256":"02b429b2694b3a84700cd730b0895e83d7f6ffa8f024d8f87e5563b08d42c6ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:47:31.745816Z","signature_b64":"J7vu6ObJJnRZkMUuZAb2DlkaUgmipbr/2YtGbnmSMH56ISnJw9NLz8dD5vu0ZWNetnNYysNqoAGa8xbznNZpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3392ea0df2ea91f5b20e1896c4bb6141bfad1b87d0ce988bb47d797e29659ee3","last_reissued_at":"2026-08-14T00:47:31.726023Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:47:31.726023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"King Bi, Larissa Xu, William Chang","submitted_at":"2026-08-13T03:06:11Z","abstract_excerpt":"We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards. Players cannot communicate during learning but may agree on a protocol a priori. For Problems A and B we propose \\texttt{mQ-learning} and \\texttt{mQ-learning-intervals}, achieving $\\tilde{O}(\\sqrt{H^4 S A_{\\text{joint}}\\, T})$ regret, where $H$ is the horizon, $S$ the state count, $T = KH$ the total"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12753","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/2608.12753/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":"2608.12753","created_at":"2026-08-14T00:47:31.736013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12753v1","created_at":"2026-08-14T00:47:31.736013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12753","created_at":"2026-08-14T00:47:31.736013+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOJOUDPS5KI7","created_at":"2026-08-14T00:47:31.736013+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOJOUDPS5KI7LMQO","created_at":"2026-08-14T00:47:31.736013+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOJOUDPS","created_at":"2026-08-14T00:47:31.736013+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/GOJOUDPS5KI7LMQODCLMJO3BIG","json":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG.json","graph_json":"https://pith.science/api/pith-number/GOJOUDPS5KI7LMQODCLMJO3BIG/graph.json","events_json":"https://pith.science/api/pith-number/GOJOUDPS5KI7LMQODCLMJO3BIG/events.json","paper":"https://pith.science/paper/GOJOUDPS"},"agent_actions":{"view_html":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG","download_json":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG.json","view_paper":"https://pith.science/paper/GOJOUDPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12753&json=true","fetch_graph":"https://pith.science/api/pith-number/GOJOUDPS5KI7LMQODCLMJO3BIG/graph.json","fetch_events":"https://pith.science/api/pith-number/GOJOUDPS5KI7LMQODCLMJO3BIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG/action/storage_attestation","attest_author":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG/action/author_attestation","sign_citation":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG/action/citation_signature","submit_replication":"https://pith.science/pith/GOJOUDPS5KI7LMQODCLMJO3BIG/action/replication_record"}},"created_at":"2026-08-14T00:47:31.736013+00:00","updated_at":"2026-08-14T00:47:31.736013+00:00"}