{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:4LUWKNSV2P6DECX6FRU5XDG3GK","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":"0a46558bd21b03805511bbe00aa90e613ed3de2179f443a61066fcd2a5cbbb04","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T03:44:42Z","title_canon_sha256":"ae0fb09ad2cb9fb6f1d03a533472afef41d4429ab4bfba53e49322ed4b1848f1"},"schema_version":"1.0","source":{"id":"1901.09311","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09311","created_at":"2026-07-05T00:07:35Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09311v2","created_at":"2026-07-05T00:07:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09311","created_at":"2026-07-05T00:07:35Z"},{"alias_kind":"pith_short_12","alias_value":"4LUWKNSV2P6D","created_at":"2026-07-05T00:07:35Z"},{"alias_kind":"pith_short_16","alias_value":"4LUWKNSV2P6DECX6","created_at":"2026-07-05T00:07:35Z"},{"alias_kind":"pith_short_8","alias_value":"4LUWKNSV","created_at":"2026-07-05T00:07:35Z"}],"graph_snapshots":[{"event_id":"sha256:5bd7817ee768ab6c180e5159fb0556d20eb772f7022e92f4caa15929559dc919","target":"graph","created_at":"2026-07-05T00:07:35Z","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/1901.09311/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A fundamental question in reinforcement learning is whether model-free algorithms are sample efficient. Recently, Jin et al. \\cite{jin2018q} proposed a Q-learning algorithm with UCB exploration policy, and proved it has nearly optimal regret bound for finite-horizon episodic MDP. In this paper, we adapt Q-learning with UCB-exploration bonus to infinite-horizon MDP with discounted rewards \\emph{without} accessing a generative model. We show that the \\textit{sample complexity of exploration} of our algorithm is bounded by $\\tilde{O}({\\frac{SA}{\\epsilon^2(1-\\gamma)^7}})$. This improves the previo","authors_text":"Kefan Dong, Liwei Wang, Xiaoyu Chen, Yuanhao Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T03:44:42Z","title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09311","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":"sha256:34ecc918e381fa9d860f269390470d441b214c683ea93130fee300cc2d11c68f","target":"record","created_at":"2026-07-05T00:07:35Z","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":"0a46558bd21b03805511bbe00aa90e613ed3de2179f443a61066fcd2a5cbbb04","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T03:44:42Z","title_canon_sha256":"ae0fb09ad2cb9fb6f1d03a533472afef41d4429ab4bfba53e49322ed4b1848f1"},"schema_version":"1.0","source":{"id":"1901.09311","kind":"arxiv","version":2}},"canonical_sha256":"e2e9653655d3fc320afe2c69db8cdb329f977f001a83e58c48f8c1bcc0208036","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2e9653655d3fc320afe2c69db8cdb329f977f001a83e58c48f8c1bcc0208036","first_computed_at":"2026-07-05T00:07:35.385365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:35.385365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldBn1I6YtFa4WJI+ts2Ldu/lzbEMxOzpbxGFSUm43zIlFTSmlgo/F5IqWIGTS5QN4Cre4Tt6O35F75Jfn9ETBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:35.385858Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09311","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34ecc918e381fa9d860f269390470d441b214c683ea93130fee300cc2d11c68f","sha256:5bd7817ee768ab6c180e5159fb0556d20eb772f7022e92f4caa15929559dc919"],"state_sha256":"91dad1f95ee68ad41bd82b78577a99a534e7b023a7ab42646881ae9d305264b7"}