{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GAP4K3PMUH5M572ZAWY6ZZZCET","short_pith_number":"pith:GAP4K3PM","schema_version":"1.0","canonical_sha256":"301fc56deca1faceff5905b1ece72224d16ee2878b01876cafbe5b69dd7c6513","source":{"kind":"arxiv","id":"1905.00475","version":1},"attestation_state":"computed","paper":{"title":"Efficient Model-free Reinforcement Learning in Metric Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Wen Sun, Zhao Song","submitted_at":"2019-05-01T20:10:24Z","abstract_excerpt":"Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with the idea of optimism in the face of uncertainty, Q-learning algorithms [Jin, Allen-Zhu, Bubeck, Jordan 18] can be proven to be sample efficient for discrete tabular Markov Decision Processes (MDPs) which have finite number of states and actions. In this work, we present an efficient model-free Q-learning based algorithm in MDPs with a natural metric on the "},"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":"1905.00475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-01T20:10:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"08ee0a5a6492a0bcad07b70d43b4c095030d200940259602a63c29c1bab00a31","abstract_canon_sha256":"ef75a873626716070efabcda0ba393464fde0e07cf02b938cca34096e9faaf2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:11.760308Z","signature_b64":"uqG1s6MuxS10PINu5QXr23KoQarD/OhCfl++/FWc34DE0+Vw++hdayJwunBTGODEpouVmluEDaq5G6SCoKfwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"301fc56deca1faceff5905b1ece72224d16ee2878b01876cafbe5b69dd7c6513","last_reissued_at":"2026-05-17T23:47:11.759794Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:11.759794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Model-free Reinforcement Learning in Metric Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Wen Sun, Zhao Song","submitted_at":"2019-05-01T20:10:24Z","abstract_excerpt":"Model-free Reinforcement Learning (RL) algorithms such as Q-learning [Watkins, Dayan 92] have been widely used in practice and can achieve human level performance in applications such as video games [Mnih et al. 15]. Recently, equipped with the idea of optimism in the face of uncertainty, Q-learning algorithms [Jin, Allen-Zhu, Bubeck, Jordan 18] can be proven to be sample efficient for discrete tabular Markov Decision Processes (MDPs) which have finite number of states and actions. In this work, we present an efficient model-free Q-learning based algorithm in MDPs with a natural metric on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00475","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1905.00475","created_at":"2026-05-17T23:47:11.759874+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.00475v1","created_at":"2026-05-17T23:47:11.759874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00475","created_at":"2026-05-17T23:47:11.759874+00:00"},{"alias_kind":"pith_short_12","alias_value":"GAP4K3PMUH5M","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GAP4K3PMUH5M572Z","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GAP4K3PM","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07218","citing_title":"Improved Model-based Reinforcement Learning with Smooth Kernels","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET","json":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET.json","graph_json":"https://pith.science/api/pith-number/GAP4K3PMUH5M572ZAWY6ZZZCET/graph.json","events_json":"https://pith.science/api/pith-number/GAP4K3PMUH5M572ZAWY6ZZZCET/events.json","paper":"https://pith.science/paper/GAP4K3PM"},"agent_actions":{"view_html":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET","download_json":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET.json","view_paper":"https://pith.science/paper/GAP4K3PM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.00475&json=true","fetch_graph":"https://pith.science/api/pith-number/GAP4K3PMUH5M572ZAWY6ZZZCET/graph.json","fetch_events":"https://pith.science/api/pith-number/GAP4K3PMUH5M572ZAWY6ZZZCET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET/action/storage_attestation","attest_author":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET/action/author_attestation","sign_citation":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET/action/citation_signature","submit_replication":"https://pith.science/pith/GAP4K3PMUH5M572ZAWY6ZZZCET/action/replication_record"}},"created_at":"2026-05-17T23:47:11.759874+00:00","updated_at":"2026-05-17T23:47:11.759874+00:00"}