{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GAP4K3PMUH5M572ZAWY6ZZZCET","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":"ef75a873626716070efabcda0ba393464fde0e07cf02b938cca34096e9faaf2e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-01T20:10:24Z","title_canon_sha256":"08ee0a5a6492a0bcad07b70d43b4c095030d200940259602a63c29c1bab00a31"},"schema_version":"1.0","source":{"id":"1905.00475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.00475","created_at":"2026-05-17T23:47:11Z"},{"alias_kind":"arxiv_version","alias_value":"1905.00475v1","created_at":"2026-05-17T23:47:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00475","created_at":"2026-05-17T23:47:11Z"},{"alias_kind":"pith_short_12","alias_value":"GAP4K3PMUH5M","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GAP4K3PMUH5M572Z","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GAP4K3PM","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:04b94ab147a9256cef739e3bd2e7df23166e011f1467c2071beedd026b9a4281","target":"graph","created_at":"2026-05-17T23:47:11Z","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"},"paper":{"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 ","authors_text":"Wen Sun, Zhao Song","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-01T20:10:24Z","title":"Efficient Model-free Reinforcement Learning in Metric Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00475","kind":"arxiv","version":1},"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":"sha256:56b59d43997f16ac6c15f6d4a8d240fb9a018ef2fd007d50e327d47e482492cb","target":"record","created_at":"2026-05-17T23:47:11Z","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":"ef75a873626716070efabcda0ba393464fde0e07cf02b938cca34096e9faaf2e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-01T20:10:24Z","title_canon_sha256":"08ee0a5a6492a0bcad07b70d43b4c095030d200940259602a63c29c1bab00a31"},"schema_version":"1.0","source":{"id":"1905.00475","kind":"arxiv","version":1}},"canonical_sha256":"301fc56deca1faceff5905b1ece72224d16ee2878b01876cafbe5b69dd7c6513","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"301fc56deca1faceff5905b1ece72224d16ee2878b01876cafbe5b69dd7c6513","first_computed_at":"2026-05-17T23:47:11.759794Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:11.759794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uqG1s6MuxS10PINu5QXr23KoQarD/OhCfl++/FWc34DE0+Vw++hdayJwunBTGODEpouVmluEDaq5G6SCoKfwAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:11.760308Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.00475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56b59d43997f16ac6c15f6d4a8d240fb9a018ef2fd007d50e327d47e482492cb","sha256:04b94ab147a9256cef739e3bd2e7df23166e011f1467c2071beedd026b9a4281"],"state_sha256":"072de03e9636012e007a870a2b40611fa1a0a3da7772fd41e3a8237a3c3a44c6"}