{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OQXYG5RLJ7UG2ARDWVVXHLHTXT","short_pith_number":"pith:OQXYG5RL","canonical_record":{"source":{"id":"1612.02516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-08T03:05:41Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"62f97b952d4be531bcd8f27d1bd94b6ef287489aa2afde83f51c9c5825dbe19c","abstract_canon_sha256":"23943e0fe3ca6b0bff5e9da6bdd4c0b5f3a61d93fad8ae0432947fb6f5135a77"},"schema_version":"1.0"},"canonical_sha256":"742f83762b4fe86d0223b56b73acf3bcfcf7955586e7b0197f64574eae7095b4","source":{"kind":"arxiv","id":"1612.02516","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02516","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02516v1","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02516","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"OQXYG5RLJ7UG","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OQXYG5RLJ7UG2ARD","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OQXYG5RL","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OQXYG5RLJ7UG2ARDWVVXHLHTXT","target":"record","payload":{"canonical_record":{"source":{"id":"1612.02516","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-08T03:05:41Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"62f97b952d4be531bcd8f27d1bd94b6ef287489aa2afde83f51c9c5825dbe19c","abstract_canon_sha256":"23943e0fe3ca6b0bff5e9da6bdd4c0b5f3a61d93fad8ae0432947fb6f5135a77"},"schema_version":"1.0"},"canonical_sha256":"742f83762b4fe86d0223b56b73acf3bcfcf7955586e7b0197f64574eae7095b4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:33.519865Z","signature_b64":"Q0HM29Rp0H4N9/oi5v7vmV8DFBRdncjLd+trZa9YnqtCMiiNazI7AiuiBlnmiQzBL6wT7kY/ST/BKytvAGXGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"742f83762b4fe86d0223b56b73acf3bcfcf7955586e7b0197f64574eae7095b4","last_reissued_at":"2026-05-18T00:55:33.519167Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:33.519167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.02516","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K6j1VuzB+FO5KVlQJk2BypCHwBOPApQS97kOtYzPiB1k6Cuv9LLww+bziymvK/OMjCDAmvfNCqJ1Gybg6bdgBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:21:01.963515Z"},"content_sha256":"1c91d476b8c77891a355c09ac36d1a2a1d3cba44cd8f9027886a6e872f59cb62","schema_version":"1.0","event_id":"sha256:1c91d476b8c77891a355c09ac36d1a2a1d3cba44cd8f9027886a6e872f59cb62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OQXYG5RLJ7UG2ARDWVVXHLHTXT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"stat.ML","authors_text":"Mengdi Wang, Yichen Chen","submitted_at":"2016-12-08T03:05:41Z","abstract_excerpt":"We study the online estimation of the optimal policy of a Markov decision process (MDP). We propose a class of Stochastic Primal-Dual (SPD) methods which exploit the inherent minimax duality of Bellman equations. The SPD methods update a few coordinates of the value and policy estimates as a new state transition is observed. These methods use small storage and has low computational complexity per iteration. The SPD methods find an absolute-$\\epsilon$-optimal policy, with high probability, using $\\mathcal{O}\\left(\\frac{|\\mathcal{S}|^4 |\\mathcal{A}|^2\\sigma^2 }{(1-\\gamma)^6\\epsilon^2} \\right)$ i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02516","kind":"arxiv","version":1},"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":"2026-05-18T00:55:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZsuSGYxVP3dVG87t4kg/w1ab+MRywGvhlVERDi6DesyKT5Dwqs/t+3pIb6Cs2J36IS8XFpshWND+wWQPqkTODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:21:01.964175Z"},"content_sha256":"6e34b652c02823c5c100bc33d4e5b3ac5180f432ee4473f8d964b9258d55ad04","schema_version":"1.0","event_id":"sha256:6e34b652c02823c5c100bc33d4e5b3ac5180f432ee4473f8d964b9258d55ad04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQXYG5RLJ7UG2ARDWVVXHLHTXT/bundle.json","state_url":"https://pith.science/pith/OQXYG5RLJ7UG2ARDWVVXHLHTXT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQXYG5RLJ7UG2ARDWVVXHLHTXT/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":"2026-05-25T15:21:01Z","links":{"resolver":"https://pith.science/pith/OQXYG5RLJ7UG2ARDWVVXHLHTXT","bundle":"https://pith.science/pith/OQXYG5RLJ7UG2ARDWVVXHLHTXT/bundle.json","state":"https://pith.science/pith/OQXYG5RLJ7UG2ARDWVVXHLHTXT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQXYG5RLJ7UG2ARDWVVXHLHTXT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OQXYG5RLJ7UG2ARDWVVXHLHTXT","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":"23943e0fe3ca6b0bff5e9da6bdd4c0b5f3a61d93fad8ae0432947fb6f5135a77","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-08T03:05:41Z","title_canon_sha256":"62f97b952d4be531bcd8f27d1bd94b6ef287489aa2afde83f51c9c5825dbe19c"},"schema_version":"1.0","source":{"id":"1612.02516","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02516","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02516v1","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02516","created_at":"2026-05-18T00:55:33Z"},{"alias_kind":"pith_short_12","alias_value":"OQXYG5RLJ7UG","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OQXYG5RLJ7UG2ARD","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OQXYG5RL","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:6e34b652c02823c5c100bc33d4e5b3ac5180f432ee4473f8d964b9258d55ad04","target":"graph","created_at":"2026-05-18T00:55:33Z","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 study the online estimation of the optimal policy of a Markov decision process (MDP). We propose a class of Stochastic Primal-Dual (SPD) methods which exploit the inherent minimax duality of Bellman equations. The SPD methods update a few coordinates of the value and policy estimates as a new state transition is observed. These methods use small storage and has low computational complexity per iteration. The SPD methods find an absolute-$\\epsilon$-optimal policy, with high probability, using $\\mathcal{O}\\left(\\frac{|\\mathcal{S}|^4 |\\mathcal{A}|^2\\sigma^2 }{(1-\\gamma)^6\\epsilon^2} \\right)$ i","authors_text":"Mengdi Wang, Yichen Chen","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-08T03:05:41Z","title":"Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02516","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":"sha256:1c91d476b8c77891a355c09ac36d1a2a1d3cba44cd8f9027886a6e872f59cb62","target":"record","created_at":"2026-05-18T00:55:33Z","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":"23943e0fe3ca6b0bff5e9da6bdd4c0b5f3a61d93fad8ae0432947fb6f5135a77","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-08T03:05:41Z","title_canon_sha256":"62f97b952d4be531bcd8f27d1bd94b6ef287489aa2afde83f51c9c5825dbe19c"},"schema_version":"1.0","source":{"id":"1612.02516","kind":"arxiv","version":1}},"canonical_sha256":"742f83762b4fe86d0223b56b73acf3bcfcf7955586e7b0197f64574eae7095b4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"742f83762b4fe86d0223b56b73acf3bcfcf7955586e7b0197f64574eae7095b4","first_computed_at":"2026-05-18T00:55:33.519167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:33.519167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q0HM29Rp0H4N9/oi5v7vmV8DFBRdncjLd+trZa9YnqtCMiiNazI7AiuiBlnmiQzBL6wT7kY/ST/BKytvAGXGAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:33.519865Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.02516","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c91d476b8c77891a355c09ac36d1a2a1d3cba44cd8f9027886a6e872f59cb62","sha256:6e34b652c02823c5c100bc33d4e5b3ac5180f432ee4473f8d964b9258d55ad04"],"state_sha256":"661f764b5087dcdc2c133b1005f2e1517f119a6eba0a8ed551a9dcf82680d350"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DokF4OQSRWF2QA0ILhix1Co9zKycmZZbMBswXJK0qFd3hdjaf/N6hzMGm4Vxj/5L3vnJBlUyuNNCZsSVarveCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:21:01.967902Z","bundle_sha256":"aeee0f65e78a523b338b5e8dd8a51e02145afa249e9645f9b9c5c744d27dda49"}}