{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4LUWKNSV2P6DECX6FRU5XDG3GK","short_pith_number":"pith:4LUWKNSV","schema_version":"1.0","canonical_sha256":"e2e9653655d3fc320afe2c69db8cdb329f977f001a83e58c48f8c1bcc0208036","source":{"kind":"arxiv","id":"1901.09311","version":2},"attestation_state":"computed","paper":{"title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kefan Dong, Liwei Wang, Xiaoyu Chen, Yuanhao Wang","submitted_at":"2019-01-27T03:44:42Z","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"},"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":"1901.09311","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T03:44:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ae0fb09ad2cb9fb6f1d03a533472afef41d4429ab4bfba53e49322ed4b1848f1","abstract_canon_sha256":"0a46558bd21b03805511bbe00aa90e613ed3de2179f443a61066fcd2a5cbbb04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:35.385858Z","signature_b64":"ldBn1I6YtFa4WJI+ts2Ldu/lzbEMxOzpbxGFSUm43zIlFTSmlgo/F5IqWIGTS5QN4Cre4Tt6O35F75Jfn9ETBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2e9653655d3fc320afe2c69db8cdb329f977f001a83e58c48f8c1bcc0208036","last_reissued_at":"2026-07-05T00:07:35.385365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:35.385365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kefan Dong, Liwei Wang, Xiaoyu Chen, Yuanhao Wang","submitted_at":"2019-01-27T03:44:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09311","kind":"arxiv","version":2},"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/1901.09311/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":"1901.09311","created_at":"2026-07-05T00:07:35.385430+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.09311v2","created_at":"2026-07-05T00:07:35.385430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09311","created_at":"2026-07-05T00:07:35.385430+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LUWKNSV2P6D","created_at":"2026-07-05T00:07:35.385430+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LUWKNSV2P6DECX6","created_at":"2026-07-05T00:07:35.385430+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LUWKNSV","created_at":"2026-07-05T00:07:35.385430+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/4LUWKNSV2P6DECX6FRU5XDG3GK","json":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK.json","graph_json":"https://pith.science/api/pith-number/4LUWKNSV2P6DECX6FRU5XDG3GK/graph.json","events_json":"https://pith.science/api/pith-number/4LUWKNSV2P6DECX6FRU5XDG3GK/events.json","paper":"https://pith.science/paper/4LUWKNSV"},"agent_actions":{"view_html":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK","download_json":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK.json","view_paper":"https://pith.science/paper/4LUWKNSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.09311&json=true","fetch_graph":"https://pith.science/api/pith-number/4LUWKNSV2P6DECX6FRU5XDG3GK/graph.json","fetch_events":"https://pith.science/api/pith-number/4LUWKNSV2P6DECX6FRU5XDG3GK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK/action/storage_attestation","attest_author":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK/action/author_attestation","sign_citation":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK/action/citation_signature","submit_replication":"https://pith.science/pith/4LUWKNSV2P6DECX6FRU5XDG3GK/action/replication_record"}},"created_at":"2026-07-05T00:07:35.385430+00:00","updated_at":"2026-07-05T00:07:35.385430+00:00"}