{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:423HKEII7SQGYBMGJHSX2QQ6W3","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":"28d8fe982e5403cc947727d5939e589f4df5da57afbf2ee368bb05262e06bdc3","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-08T02:05:40Z","title_canon_sha256":"b1a2fe442de20431a36433bc774a65e207d2e015ab97e7009eb39bae4923e563"},"schema_version":"1.0","source":{"id":"2109.03396","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03396","created_at":"2026-07-05T07:54:28Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03396v3","created_at":"2026-07-05T07:54:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03396","created_at":"2026-07-05T07:54:28Z"},{"alias_kind":"pith_short_12","alias_value":"423HKEII7SQG","created_at":"2026-07-05T07:54:28Z"},{"alias_kind":"pith_short_16","alias_value":"423HKEII7SQGYBMG","created_at":"2026-07-05T07:54:28Z"},{"alias_kind":"pith_short_8","alias_value":"423HKEII","created_at":"2026-07-05T07:54:28Z"}],"graph_snapshots":[{"event_id":"sha256:949d61eb4e83ec4c2fd0c13e2263d7c5d226ef023abf8e352bef44a56497b678","target":"graph","created_at":"2026-07-05T07:54:28Z","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/2109.03396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose Posterior Sampling Reinforcement Learning for Zero-sum Stochastic Games (PSRL-ZSG), the first online learning algorithm that achieves Bayesian regret bound of $O(HS\\sqrt{AT})$ in the infinite-horizon zero-sum stochastic games with average-reward criterion. Here $H$ is an upper bound on the span of the bias function, $S$ is the number of states, $A$ is the number of joint actions and $T$ is the horizon. We consider the online setting where the opponent can not be controlled and can take any arbitrary time-adaptive history-dependent strategy. Our regret bound improves o","authors_text":"Ashutosh Nayyar, Mehdi Jafarnia-Jahromi, Rahul Jain","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-08T02:05:40Z","title":"A Bayesian Learning Algorithm for Unknown Zero-sum Stochastic Games with an Arbitrary Opponent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03396","kind":"arxiv","version":3},"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":"sha256:50d48458f84add3077636acdf10556b9cd96392296a499fb9da29502f435c97e","target":"record","created_at":"2026-07-05T07:54:28Z","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":"28d8fe982e5403cc947727d5939e589f4df5da57afbf2ee368bb05262e06bdc3","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-08T02:05:40Z","title_canon_sha256":"b1a2fe442de20431a36433bc774a65e207d2e015ab97e7009eb39bae4923e563"},"schema_version":"1.0","source":{"id":"2109.03396","kind":"arxiv","version":3}},"canonical_sha256":"e6b6751108fca06c058649e57d421eb6ef7d7a3669ad47077b6b97f2ed3232ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6b6751108fca06c058649e57d421eb6ef7d7a3669ad47077b6b97f2ed3232ab","first_computed_at":"2026-07-05T07:54:28.536873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:28.536873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u2rQBhreWGmxFc+v43a+ACCnNRDvh8RfsmlKxeajdLaO/cpkgHClIf4n/yBYR2oxuBkqyiKQvS++xi63HpwKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:28.537298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.03396","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50d48458f84add3077636acdf10556b9cd96392296a499fb9da29502f435c97e","sha256:949d61eb4e83ec4c2fd0c13e2263d7c5d226ef023abf8e352bef44a56497b678"],"state_sha256":"c51e52cebead7886f8c938c9a89936a2548da786341e847fddd08444f30527eb"}