{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:JPNENFCPQJA4RQ7N7ST3JADRUF","short_pith_number":"pith:JPNENFCP","schema_version":"1.0","canonical_sha256":"4bda46944f8241c8c3edfca7b48071a17034f4b18d625b0f97f39406ea44bfe9","source":{"kind":"arxiv","id":"1802.03900","version":2},"attestation_state":"computed","paper":{"title":"Q-learning with Nearest Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Devavrat Shah, Qiaomin Xie","submitted_at":"2018-02-12T05:54:43Z","abstract_excerpt":"We consider model-free reinforcement learning for infinite-horizon discounted Markov Decision Processes (MDPs) with a continuous state space and unknown transition kernel, when only a single sample path under an arbitrary policy of the system is available. We consider the Nearest Neighbor Q-Learning (NNQL) algorithm to learn the optimal Q function using nearest neighbor regression method. As the main contribution, we provide tight finite sample analysis of the convergence rate. In particular, for MDPs with a $d$-dimensional state space and the discounted factor $\\gamma \\in (0,1)$, given an arb"},"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":"1802.03900","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T05:54:43Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"2c28d1e411a7ac58a778b8fdfa988253e1846ccb1c8a6f000965c1128ae75bb9","abstract_canon_sha256":"c460b8efd9cc5bee395592c71f8ba6cb5556633119db3b4ee37f51fe80cdb062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:39.732432Z","signature_b64":"WY+KlvHsY6Euyo18gX6JqjHrt+RWRM7DYlqGWRXZbF9yneQTORvKbrpGQoze8EZ+Hhp2hsz6ZZu803lhoQG7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bda46944f8241c8c3edfca7b48071a17034f4b18d625b0f97f39406ea44bfe9","last_reissued_at":"2026-05-18T00:02:39.731756Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:39.731756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-learning with Nearest Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Devavrat Shah, Qiaomin Xie","submitted_at":"2018-02-12T05:54:43Z","abstract_excerpt":"We consider model-free reinforcement learning for infinite-horizon discounted Markov Decision Processes (MDPs) with a continuous state space and unknown transition kernel, when only a single sample path under an arbitrary policy of the system is available. We consider the Nearest Neighbor Q-Learning (NNQL) algorithm to learn the optimal Q function using nearest neighbor regression method. As the main contribution, we provide tight finite sample analysis of the convergence rate. In particular, for MDPs with a $d$-dimensional state space and the discounted factor $\\gamma \\in (0,1)$, given an arb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03900","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":""},"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":"1802.03900","created_at":"2026-05-18T00:02:39.731878+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.03900v2","created_at":"2026-05-18T00:02:39.731878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03900","created_at":"2026-05-18T00:02:39.731878+00:00"},{"alias_kind":"pith_short_12","alias_value":"JPNENFCPQJA4","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"JPNENFCPQJA4RQ7N","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"JPNENFCP","created_at":"2026-05-18T12:32:31.084164+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/JPNENFCPQJA4RQ7N7ST3JADRUF","json":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF.json","graph_json":"https://pith.science/api/pith-number/JPNENFCPQJA4RQ7N7ST3JADRUF/graph.json","events_json":"https://pith.science/api/pith-number/JPNENFCPQJA4RQ7N7ST3JADRUF/events.json","paper":"https://pith.science/paper/JPNENFCP"},"agent_actions":{"view_html":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF","download_json":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF.json","view_paper":"https://pith.science/paper/JPNENFCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.03900&json=true","fetch_graph":"https://pith.science/api/pith-number/JPNENFCPQJA4RQ7N7ST3JADRUF/graph.json","fetch_events":"https://pith.science/api/pith-number/JPNENFCPQJA4RQ7N7ST3JADRUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/action/storage_attestation","attest_author":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/action/author_attestation","sign_citation":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/action/citation_signature","submit_replication":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/action/replication_record"}},"created_at":"2026-05-18T00:02:39.731878+00:00","updated_at":"2026-05-18T00:02:39.731878+00:00"}