{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JPNENFCPQJA4RQ7N7ST3JADRUF","short_pith_number":"pith:JPNENFCP","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"},"canonical_sha256":"4bda46944f8241c8c3edfca7b48071a17034f4b18d625b0f97f39406ea44bfe9","source":{"kind":"arxiv","id":"1802.03900","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03900","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03900v2","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03900","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"JPNENFCPQJA4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JPNENFCPQJA4RQ7N","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JPNENFCP","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JPNENFCPQJA4RQ7N7ST3JADRUF","target":"record","payload":{"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"},"canonical_sha256":"4bda46944f8241c8c3edfca7b48071a17034f4b18d625b0f97f39406ea44bfe9","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"},"source_kind":"arxiv","source_id":"1802.03900","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXBkJcPO/+iaNH3jABtjeLTC9sg5BYgXJ0GhXggW0xnisroMsPkCPVzYATDAKZ+M1Vim9RpO8rFYxiv2zDA5CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:55:30.277060Z"},"content_sha256":"c19dcaa02398be0f422035b6a58c21079435af651cf5ca4584bfd391df25dcf3","schema_version":"1.0","event_id":"sha256:c19dcaa02398be0f422035b6a58c21079435af651cf5ca4584bfd391df25dcf3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JPNENFCPQJA4RQ7N7ST3JADRUF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bB+3j9PhpCXysPlpCumeCu0Zm6/3KlVs2kIrPsH+0mKXoQaMy0rF/wsfMz/qVcInf7GoO5ciBwrOuRrDoL4RCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T19:55:30.277420Z"},"content_sha256":"6a1517ed0a6b6150cd85cb8c3f8de5155c20c6b5cdd0b379461f7fbdd42a4c48","schema_version":"1.0","event_id":"sha256:6a1517ed0a6b6150cd85cb8c3f8de5155c20c6b5cdd0b379461f7fbdd42a4c48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/bundle.json","state_url":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T19:55:30Z","links":{"resolver":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF","bundle":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/bundle.json","state":"https://pith.science/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPNENFCPQJA4RQ7N7ST3JADRUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JPNENFCPQJA4RQ7N7ST3JADRUF","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":"c460b8efd9cc5bee395592c71f8ba6cb5556633119db3b4ee37f51fe80cdb062","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T05:54:43Z","title_canon_sha256":"2c28d1e411a7ac58a778b8fdfa988253e1846ccb1c8a6f000965c1128ae75bb9"},"schema_version":"1.0","source":{"id":"1802.03900","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.03900","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"1802.03900v2","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.03900","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"JPNENFCPQJA4","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JPNENFCPQJA4RQ7N","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JPNENFCP","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:6a1517ed0a6b6150cd85cb8c3f8de5155c20c6b5cdd0b379461f7fbdd42a4c48","target":"graph","created_at":"2026-05-18T00:02:39Z","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":"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","authors_text":"Devavrat Shah, Qiaomin Xie","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T05:54:43Z","title":"Q-learning with Nearest Neighbors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.03900","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:c19dcaa02398be0f422035b6a58c21079435af651cf5ca4584bfd391df25dcf3","target":"record","created_at":"2026-05-18T00:02:39Z","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":"c460b8efd9cc5bee395592c71f8ba6cb5556633119db3b4ee37f51fe80cdb062","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T05:54:43Z","title_canon_sha256":"2c28d1e411a7ac58a778b8fdfa988253e1846ccb1c8a6f000965c1128ae75bb9"},"schema_version":"1.0","source":{"id":"1802.03900","kind":"arxiv","version":2}},"canonical_sha256":"4bda46944f8241c8c3edfca7b48071a17034f4b18d625b0f97f39406ea44bfe9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bda46944f8241c8c3edfca7b48071a17034f4b18d625b0f97f39406ea44bfe9","first_computed_at":"2026-05-18T00:02:39.731756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:39.731756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WY+KlvHsY6Euyo18gX6JqjHrt+RWRM7DYlqGWRXZbF9yneQTORvKbrpGQoze8EZ+Hhp2hsz6ZZu803lhoQG7AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:39.732432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.03900","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c19dcaa02398be0f422035b6a58c21079435af651cf5ca4584bfd391df25dcf3","sha256:6a1517ed0a6b6150cd85cb8c3f8de5155c20c6b5cdd0b379461f7fbdd42a4c48"],"state_sha256":"118ebb3e3b63d1826f94c9097ad66dfe321546d44ff5745d5087f98edb5275d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBFZbjtKAfuA2U9oCa925049VXz9N8iIHeQRcWDXqksS5LaAMkcdmumrcnNnngoDA2zDFndAgE0LZgNTtaelBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T19:55:30.279352Z","bundle_sha256":"98572fd2afea8083c80f4d7bc78bfc5e44fead6681df0119a800d0f74d1b128a"}}