{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DVGZ33QGUVYMKUPJXC5ZELC6MV","short_pith_number":"pith:DVGZ33QG","canonical_record":{"source":{"id":"1806.01492","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-06-05T04:34:54Z","cross_cats_sorted":[],"title_canon_sha256":"2868beb5fde9e37c85483f987687620152b4ac7203bf38f377565de60d777078","abstract_canon_sha256":"953d6e186b505d7ab56a6c0974701bb91ce5c67a58be90adb4913a68b69f0092"},"schema_version":"1.0"},"canonical_sha256":"1d4d9dee06a570c551e9b8bb922c5e656e461f27f9c45ad7d1ac04f2f64b41ab","source":{"kind":"arxiv","id":"1806.01492","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01492","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01492v3","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01492","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"DVGZ33QGUVYM","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DVGZ33QGUVYMKUPJ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DVGZ33QG","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DVGZ33QGUVYMKUPJXC5ZELC6MV","target":"record","payload":{"canonical_record":{"source":{"id":"1806.01492","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-06-05T04:34:54Z","cross_cats_sorted":[],"title_canon_sha256":"2868beb5fde9e37c85483f987687620152b4ac7203bf38f377565de60d777078","abstract_canon_sha256":"953d6e186b505d7ab56a6c0974701bb91ce5c67a58be90adb4913a68b69f0092"},"schema_version":"1.0"},"canonical_sha256":"1d4d9dee06a570c551e9b8bb922c5e656e461f27f9c45ad7d1ac04f2f64b41ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.958247Z","signature_b64":"H6joWHEYGupRRcrPbn3yT6LJFYUX7B2Jfm/3sF/aqDDT9V31Lr2FSB/eNVNNZYGqybw4zVLeLxfJaBcmtSiFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d4d9dee06a570c551e9b8bb922c5e656e461f27f9c45ad7d1ac04f2f64b41ab","last_reissued_at":"2026-05-17T23:44:02.957692Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.957692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.01492","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":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"51QxPzMqKXq78VGw4hAg7Jj2N34CawDn0pULrIhN2OysxnW8PfSyWgVMgD5w4UYlcreKocUrRfSG+bKWX7njCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:27:27.814928Z"},"content_sha256":"937290933a715b08d185b9731e0b5099b1b375f703b7818f5bab307cd7c45c27","schema_version":"1.0","event_id":"sha256:937290933a715b08d185b9731e0b5099b1b375f703b7818f5bab307cd7c45c27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DVGZ33QGUVYMKUPJXC5ZELC6MV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Aaron Sidford, Lin F. Yang, Mengdi Wang, Xian Wu, Yinyu Ye","submitted_at":"2018-06-05T04:34:54Z","abstract_excerpt":"In this paper we consider the problem of computing an $\\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any state-action pair samples from the transition function in $O(1)$ time. Given such a DMDP with states $S$, actions $A$, discount factor $\\gamma\\in(0,1)$, and rewards in range $[0, 1]$ we provide an algorithm which computes an $\\epsilon$-optimal policy with probability $1 - \\delta$ where \\emph{both} the time spent and number of sample taken are upper bounded by \\[ O\\lef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01492","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":""},"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":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SmPfupIUO/jNuPYoVLzOzdpB+saJGL9Uyffjkxk1V5bsZh03DprQIOABhhpacRcIp3qhymHmfGnWsT3QlCtzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:27:27.815729Z"},"content_sha256":"2d7c0bf7f96118a22b38fbaf8650dc1fb52e4ad71f6c2442f15ef1a1653d5e9c","schema_version":"1.0","event_id":"sha256:2d7c0bf7f96118a22b38fbaf8650dc1fb52e4ad71f6c2442f15ef1a1653d5e9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/bundle.json","state_url":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/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":"2026-05-31T12:27:27Z","links":{"resolver":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV","bundle":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/bundle.json","state":"https://pith.science/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVGZ33QGUVYMKUPJXC5ZELC6MV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DVGZ33QGUVYMKUPJXC5ZELC6MV","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":"953d6e186b505d7ab56a6c0974701bb91ce5c67a58be90adb4913a68b69f0092","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-06-05T04:34:54Z","title_canon_sha256":"2868beb5fde9e37c85483f987687620152b4ac7203bf38f377565de60d777078"},"schema_version":"1.0","source":{"id":"1806.01492","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.01492","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1806.01492v3","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.01492","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"DVGZ33QGUVYM","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DVGZ33QGUVYMKUPJ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DVGZ33QG","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:2d7c0bf7f96118a22b38fbaf8650dc1fb52e4ad71f6c2442f15ef1a1653d5e9c","target":"graph","created_at":"2026-05-17T23:44:02Z","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":"In this paper we consider the problem of computing an $\\epsilon$-optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through a generative sampling model that given any state-action pair samples from the transition function in $O(1)$ time. Given such a DMDP with states $S$, actions $A$, discount factor $\\gamma\\in(0,1)$, and rewards in range $[0, 1]$ we provide an algorithm which computes an $\\epsilon$-optimal policy with probability $1 - \\delta$ where \\emph{both} the time spent and number of sample taken are upper bounded by \\[ O\\lef","authors_text":"Aaron Sidford, Lin F. Yang, Mengdi Wang, Xian Wu, Yinyu Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-06-05T04:34:54Z","title":"Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.01492","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":"sha256:937290933a715b08d185b9731e0b5099b1b375f703b7818f5bab307cd7c45c27","target":"record","created_at":"2026-05-17T23:44:02Z","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":"953d6e186b505d7ab56a6c0974701bb91ce5c67a58be90adb4913a68b69f0092","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-06-05T04:34:54Z","title_canon_sha256":"2868beb5fde9e37c85483f987687620152b4ac7203bf38f377565de60d777078"},"schema_version":"1.0","source":{"id":"1806.01492","kind":"arxiv","version":3}},"canonical_sha256":"1d4d9dee06a570c551e9b8bb922c5e656e461f27f9c45ad7d1ac04f2f64b41ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d4d9dee06a570c551e9b8bb922c5e656e461f27f9c45ad7d1ac04f2f64b41ab","first_computed_at":"2026-05-17T23:44:02.957692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:02.957692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H6joWHEYGupRRcrPbn3yT6LJFYUX7B2Jfm/3sF/aqDDT9V31Lr2FSB/eNVNNZYGqybw4zVLeLxfJaBcmtSiFDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:02.958247Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.01492","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:937290933a715b08d185b9731e0b5099b1b375f703b7818f5bab307cd7c45c27","sha256:2d7c0bf7f96118a22b38fbaf8650dc1fb52e4ad71f6c2442f15ef1a1653d5e9c"],"state_sha256":"2d24905e29516ab0c78ea106c9b403f8fdee2f0f0b5e49df9fe77ccc0217e02b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lgn6J+qjpt60lzkHxgFAWJT35vmiPUB7KJwdi56eeEyBxShAt/tEgDWXpZYoB2lNqJGHaBCA7x45l026H1nHCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T12:27:27.820429Z","bundle_sha256":"504a2129086c7512a24c2e8a0a504e972202ec5cad85e8f1eb44e82ffd3439cd"}}