{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:Q74FXGJ6JGKTQWSDL4IP4MOXTR","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":"fcdea76ebe6292aca0c089e3008868db3adbd69451f72e9ef93e2473713cc905","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2021-12-15T03:33:39Z","title_canon_sha256":"7ed88e226585c7117eb5c9503671a19a663613a76fffd7d6b33fdb7387958fb9"},"schema_version":"1.0","source":{"id":"2112.07859","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07859","created_at":"2026-07-05T03:41:28Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07859v2","created_at":"2026-07-05T03:41:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07859","created_at":"2026-07-05T03:41:28Z"},{"alias_kind":"pith_short_12","alias_value":"Q74FXGJ6JGKT","created_at":"2026-07-05T03:41:28Z"},{"alias_kind":"pith_short_16","alias_value":"Q74FXGJ6JGKTQWSD","created_at":"2026-07-05T03:41:28Z"},{"alias_kind":"pith_short_8","alias_value":"Q74FXGJ6","created_at":"2026-07-05T03:41:28Z"}],"graph_snapshots":[{"event_id":"sha256:ace2a639074840c6c233f79552b08d3d326b45bec02358c887734f70977eeaa3","target":"graph","created_at":"2026-07-05T03:41:28Z","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/2112.07859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning in stochastic games is arguably the most standard and fundamental setting in multi-agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in stochastic games in the non-asymptotic regime. In particular, we establish the finite-sample complexity of fully decentralized Q-learning algorithms in a significant class of general-sum stochastic games (SGs) - weakly acyclic SGs, which includes the common cooperative MARL setting with an identical reward to all agents (a Markov team problem) as a special case. We focus on the practical while challenging setting of fu","authors_text":"John R. Birge, Qianqian Ma, Tamer Ba\\c{s}ar, Zuguang Gao","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2021-12-15T03:33:39Z","title":"Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07859","kind":"arxiv","version":2},"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":"sha256:8f16296e0f83ffd8fd56e44346073bd48179d42e7607b6050edf127f9448eea6","target":"record","created_at":"2026-07-05T03:41:28Z","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":"fcdea76ebe6292aca0c089e3008868db3adbd69451f72e9ef93e2473713cc905","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2021-12-15T03:33:39Z","title_canon_sha256":"7ed88e226585c7117eb5c9503671a19a663613a76fffd7d6b33fdb7387958fb9"},"schema_version":"1.0","source":{"id":"2112.07859","kind":"arxiv","version":2}},"canonical_sha256":"87f85b993e4995385a435f10fe31d79c4e8dfa6ef8f55736e1c506a39da8a0cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87f85b993e4995385a435f10fe31d79c4e8dfa6ef8f55736e1c506a39da8a0cb","first_computed_at":"2026-07-05T03:41:28.670464Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:41:28.670464Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8k6zdKFxp8mJcwRzrpxKXABFzozKaQOkjL3vDZZhNNKAC4NxkiH9EkmTz7XbKgyh4UAq6Mf0FElzppVdoPi+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:41:28.670943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07859","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f16296e0f83ffd8fd56e44346073bd48179d42e7607b6050edf127f9448eea6","sha256:ace2a639074840c6c233f79552b08d3d326b45bec02358c887734f70977eeaa3"],"state_sha256":"e2294301856d7939a812055f8016ed00d40b9711cd5c0c04df56d5ae1fe508d9"}