{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GOJOUDPS5KI7LMQODCLMJO3BIG","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":"02b429b2694b3a84700cd730b0895e83d7f6ffa8f024d8f87e5563b08d42c6ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T03:06:11Z","title_canon_sha256":"1d534f48bf875467bc9db317c438a3d6693c12fddd36c5a1508a7ac5b6e89ebe"},"schema_version":"1.0","source":{"id":"2608.12753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12753","created_at":"2026-08-14T00:47:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12753v1","created_at":"2026-08-14T00:47:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12753","created_at":"2026-08-14T00:47:31Z"},{"alias_kind":"pith_short_12","alias_value":"GOJOUDPS5KI7","created_at":"2026-08-14T00:47:31Z"},{"alias_kind":"pith_short_16","alias_value":"GOJOUDPS5KI7LMQO","created_at":"2026-08-14T00:47:31Z"},{"alias_kind":"pith_short_8","alias_value":"GOJOUDPS","created_at":"2026-08-14T00:47:31Z"}],"graph_snapshots":[{"event_id":"sha256:2b86ea111a77e87ca576a4a9f63008d3afdb6a73ee6d21fdfcf56eb257f6d49a","target":"graph","created_at":"2026-08-14T00:47:31Z","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/2608.12753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"King Bi, Larissa Xu, William Chang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T03:06:11Z","title":"Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12753","kind":"arxiv","version":1},"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":"sha256:1fe3c60176539a706562da6947cb422dc2997deff1c12257afaebf0ffd1cf301","target":"record","created_at":"2026-08-14T00:47:31Z","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":"02b429b2694b3a84700cd730b0895e83d7f6ffa8f024d8f87e5563b08d42c6ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T03:06:11Z","title_canon_sha256":"1d534f48bf875467bc9db317c438a3d6693c12fddd36c5a1508a7ac5b6e89ebe"},"schema_version":"1.0","source":{"id":"2608.12753","kind":"arxiv","version":1}},"canonical_sha256":"3392ea0df2ea91f5b20e1896c4bb6141bfad1b87d0ce988bb47d797e29659ee3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3392ea0df2ea91f5b20e1896c4bb6141bfad1b87d0ce988bb47d797e29659ee3","first_computed_at":"2026-08-14T00:47:31.726023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:47:31.726023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J7vu6ObJJnRZkMUuZAb2DlkaUgmipbr/2YtGbnmSMH56ISnJw9NLz8dD5vu0ZWNetnNYysNqoAGa8xbznNZpCQ==","signature_status":"signed_v1","signed_at":"2026-08-14T00:47:31.745816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fe3c60176539a706562da6947cb422dc2997deff1c12257afaebf0ffd1cf301","sha256:2b86ea111a77e87ca576a4a9f63008d3afdb6a73ee6d21fdfcf56eb257f6d49a"],"state_sha256":"097826895380f1acbef017fcf382e4c9749705ded640dedb46f75f12a1d0ce62"}