{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IVHZQLW7SSPTPBWCMZA6YKSRN4","short_pith_number":"pith:IVHZQLW7","canonical_record":{"source":{"id":"2006.03041","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-04T17:51:00Z","cross_cats_sorted":["eess.SP","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2c7ea6aeac0be2212a053825d3e830707d0977075a1094e788902d671a639793","abstract_canon_sha256":"b246c9316d9507ad6c5bc8d4f098e817f935311f964e8d49b3168b2d8fc3642a"},"schema_version":"1.0"},"canonical_sha256":"454f982edf949f3786c26641ec2a516f2b9a67f849222e0bc3ca8a987600fd6a","source":{"kind":"arxiv","id":"2006.03041","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.03041","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"2006.03041v3","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03041","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"IVHZQLW7SSPT","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_16","alias_value":"IVHZQLW7SSPTPBWC","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_8","alias_value":"IVHZQLW7","created_at":"2026-07-05T04:56:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IVHZQLW7SSPTPBWCMZA6YKSRN4","target":"record","payload":{"canonical_record":{"source":{"id":"2006.03041","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-04T17:51:00Z","cross_cats_sorted":["eess.SP","math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"2c7ea6aeac0be2212a053825d3e830707d0977075a1094e788902d671a639793","abstract_canon_sha256":"b246c9316d9507ad6c5bc8d4f098e817f935311f964e8d49b3168b2d8fc3642a"},"schema_version":"1.0"},"canonical_sha256":"454f982edf949f3786c26641ec2a516f2b9a67f849222e0bc3ca8a987600fd6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:56:09.244402Z","signature_b64":"HAjxvuy7HVDyWCAVsbGAf7emKIlOZOWsXS1KjDl9rOnw1ZMkvkvRuMnvFGEZDEzo2yX4Gn++irGs0gM4H/H/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454f982edf949f3786c26641ec2a516f2b9a67f849222e0bc3ca8a987600fd6a","last_reissued_at":"2026-07-05T04:56:09.243908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:56:09.243908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.03041","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZD1NF5V19kjJh27zSycYtd5LboIPIxShFU98D7ISbcLr13udJfpz7lj7DDa4K0g8XwtjQGj//rYf0HnYBO/SBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:56:26.917377Z"},"content_sha256":"550fec631cb6deb4dadc087a986cdbd73eca845e2dcf935fe90eaa3a569c7e34","schema_version":"1.0","event_id":"sha256:550fec631cb6deb4dadc087a986cdbd73eca845e2dcf935fe90eaa3a569c7e34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IVHZQLW7SSPTPBWCMZA6YKSRN4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP","math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Gen Li, Yuantao Gu, Yuejie Chi, Yuting Wei, Yuxin Chen","submitted_at":"2020-06-04T17:51:00Z","abstract_excerpt":"Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP), based on a single trajectory of Markovian samples induced by a behavior policy. Focusing on a $\\gamma$-discounted MDP with state space $\\mathcal{S}$ and action space $\\mathcal{A}$, we demonstrate that the $\\ell_{\\infty}$-based sample complexity of classical asynchronous Q-learning --- namely, the number of samples needed to yield an entrywise $\\varepsilon$-accurate estimate of the Q-function --- is at most on the order of $\\frac{1}{\\mu_{\\min}(1-\\gamma)^5\\varepsilon^2}+ \\f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03041","kind":"arxiv","version":3},"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/2006.03041/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:56:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nO+C3BsQm2VE+CuC7fm4VtsTEcpUiUGUf2Aibgjkq8i6Pf3XJiR4H/5XfU2ERZqQwu/F0wXfEmXI4qRrI5tZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T23:56:26.917765Z"},"content_sha256":"47672191178f1df69426e32de410fe85959874729612b499fb7fef3b7963d7f1","schema_version":"1.0","event_id":"sha256:47672191178f1df69426e32de410fe85959874729612b499fb7fef3b7963d7f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVHZQLW7SSPTPBWCMZA6YKSRN4/bundle.json","state_url":"https://pith.science/pith/IVHZQLW7SSPTPBWCMZA6YKSRN4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVHZQLW7SSPTPBWCMZA6YKSRN4/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":"2026-07-24T23:56:26Z","links":{"resolver":"https://pith.science/pith/IVHZQLW7SSPTPBWCMZA6YKSRN4","bundle":"https://pith.science/pith/IVHZQLW7SSPTPBWCMZA6YKSRN4/bundle.json","state":"https://pith.science/pith/IVHZQLW7SSPTPBWCMZA6YKSRN4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVHZQLW7SSPTPBWCMZA6YKSRN4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IVHZQLW7SSPTPBWCMZA6YKSRN4","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":"b246c9316d9507ad6c5bc8d4f098e817f935311f964e8d49b3168b2d8fc3642a","cross_cats_sorted":["eess.SP","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-04T17:51:00Z","title_canon_sha256":"2c7ea6aeac0be2212a053825d3e830707d0977075a1094e788902d671a639793"},"schema_version":"1.0","source":{"id":"2006.03041","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.03041","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"arxiv_version","alias_value":"2006.03041v3","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.03041","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_12","alias_value":"IVHZQLW7SSPT","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_16","alias_value":"IVHZQLW7SSPTPBWC","created_at":"2026-07-05T04:56:09Z"},{"alias_kind":"pith_short_8","alias_value":"IVHZQLW7","created_at":"2026-07-05T04:56:09Z"}],"graph_snapshots":[{"event_id":"sha256:47672191178f1df69426e32de410fe85959874729612b499fb7fef3b7963d7f1","target":"graph","created_at":"2026-07-05T04:56:09Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.03041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP), based on a single trajectory of Markovian samples induced by a behavior policy. Focusing on a $\\gamma$-discounted MDP with state space $\\mathcal{S}$ and action space $\\mathcal{A}$, we demonstrate that the $\\ell_{\\infty}$-based sample complexity of classical asynchronous Q-learning --- namely, the number of samples needed to yield an entrywise $\\varepsilon$-accurate estimate of the Q-function --- is at most on the order of $\\frac{1}{\\mu_{\\min}(1-\\gamma)^5\\varepsilon^2}+ \\f","authors_text":"Gen Li, Yuantao Gu, Yuejie Chi, Yuting Wei, Yuxin Chen","cross_cats":["eess.SP","math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-04T17:51:00Z","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.03041","kind":"arxiv","version":3},"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":"sha256:550fec631cb6deb4dadc087a986cdbd73eca845e2dcf935fe90eaa3a569c7e34","target":"record","created_at":"2026-07-05T04:56:09Z","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":"b246c9316d9507ad6c5bc8d4f098e817f935311f964e8d49b3168b2d8fc3642a","cross_cats_sorted":["eess.SP","math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-04T17:51:00Z","title_canon_sha256":"2c7ea6aeac0be2212a053825d3e830707d0977075a1094e788902d671a639793"},"schema_version":"1.0","source":{"id":"2006.03041","kind":"arxiv","version":3}},"canonical_sha256":"454f982edf949f3786c26641ec2a516f2b9a67f849222e0bc3ca8a987600fd6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"454f982edf949f3786c26641ec2a516f2b9a67f849222e0bc3ca8a987600fd6a","first_computed_at":"2026-07-05T04:56:09.243908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:56:09.243908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HAjxvuy7HVDyWCAVsbGAf7emKIlOZOWsXS1KjDl9rOnw1ZMkvkvRuMnvFGEZDEzo2yX4Gn++irGs0gM4H/H/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:56:09.244402Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.03041","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:550fec631cb6deb4dadc087a986cdbd73eca845e2dcf935fe90eaa3a569c7e34","sha256:47672191178f1df69426e32de410fe85959874729612b499fb7fef3b7963d7f1"],"state_sha256":"7ef9319ac9a1b26e8be96a4099364ca7a3549feb031b497542781aef2d2ca456"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wvX+v9Ietttkn4otBmDoUhHcHf2/+oPn+gshzBZQJqtFzOmbxUhyvJA/E0OjG6v/c+3kRWoOMgCTnvEitd0fAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T23:56:26.919998Z","bundle_sha256":"9e49da81f8fa331df722702b035208c6aeaba7ffe377979bd8deb54b5c091918"}}