{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:6R25VUJ7AMEXHXO5TYXYLJ2Y47","short_pith_number":"pith:6R25VUJ7","canonical_record":{"source":{"id":"2212.00603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T15:57:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14142370df77e2bf28cfaeb11b2e53f1e283ea4c6a14d64f1ac974e434933825","abstract_canon_sha256":"8d1774501a6a522a25769eda6acb4f4af687fc8674a5a4a564ab712ec91af3be"},"schema_version":"1.0"},"canonical_sha256":"f475dad13f030973dddd9e2f85a758e7c069e38861ac5a117780d979c69d58a3","source":{"kind":"arxiv","id":"2212.00603","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00603","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00603v1","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00603","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"pith_short_12","alias_value":"6R25VUJ7AMEX","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"pith_short_16","alias_value":"6R25VUJ7AMEXHXO5","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"pith_short_8","alias_value":"6R25VUJ7","created_at":"2026-07-05T05:21:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:6R25VUJ7AMEXHXO5TYXYLJ2Y47","target":"record","payload":{"canonical_record":{"source":{"id":"2212.00603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T15:57:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14142370df77e2bf28cfaeb11b2e53f1e283ea4c6a14d64f1ac974e434933825","abstract_canon_sha256":"8d1774501a6a522a25769eda6acb4f4af687fc8674a5a4a564ab712ec91af3be"},"schema_version":"1.0"},"canonical_sha256":"f475dad13f030973dddd9e2f85a758e7c069e38861ac5a117780d979c69d58a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:36.022998Z","signature_b64":"9bEb9nuHxsWQ84FWjSwFgbJYE91/Xut7oT8pjxKUFH39mvhZtwoGzRpoZjrn7Dtr/So/A3+GKFwooxR50PZpBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f475dad13f030973dddd9e2f85a758e7c069e38861ac5a117780d979c69d58a3","last_reissued_at":"2026-07-05T05:21:36.022658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:36.022658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.00603","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":"2026-07-05T05:21:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udRljjgshOGmHkpRVqrlqDCH80CByMbSmjCt6GcZyPl9uxzOBwORvOkN4Gns9o/1oUSoHzgn9QHmJTqV3KYICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:33:36.807802Z"},"content_sha256":"bd333b9b2eb980b040447488ef539a38ddc253f6caa229a1503039ae7e891385","schema_version":"1.0","event_id":"sha256:bd333b9b2eb980b040447488ef539a38ddc253f6caa229a1503039ae7e891385"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:6R25VUJ7AMEXHXO5TYXYLJ2Y47","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jinghan Wang, Lin F. Yang, Mengdi Wang","submitted_at":"2022-12-01T15:57:58Z","abstract_excerpt":"This work considers the sample complexity of obtaining an $\\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating, we prove an upper bound of $\\widetilde O(H \\varepsilon^{-3} \\ln \\frac{1}{\\delta})$ samples per state-action pair, where $H := sp(h^*)$ is the span of bias of any optimal policy, $\\varepsilon$ is the accuracy and $\\delta$ is the failure probability. This bound improves the best-known mixing-time-based approaches in [Jin & Sidford 2021], which assume the mixing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00603","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.00603/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":"2026-07-05T05:21:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qwu9WXE7CT/T5tZF+Xs2vmw1BJtnhodVfEGgqAuGJ+JzLEAHIGSqaf2IV87ntDSl8as1Mx6pxszkv8KogZM3Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:33:36.808325Z"},"content_sha256":"354c745de3df11dd48739474639b821873c70fd328b2d88cbfbbc74d4a61e423","schema_version":"1.0","event_id":"sha256:354c745de3df11dd48739474639b821873c70fd328b2d88cbfbbc74d4a61e423"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6R25VUJ7AMEXHXO5TYXYLJ2Y47/bundle.json","state_url":"https://pith.science/pith/6R25VUJ7AMEXHXO5TYXYLJ2Y47/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6R25VUJ7AMEXHXO5TYXYLJ2Y47/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":"2026-08-07T18:33:36Z","links":{"resolver":"https://pith.science/pith/6R25VUJ7AMEXHXO5TYXYLJ2Y47","bundle":"https://pith.science/pith/6R25VUJ7AMEXHXO5TYXYLJ2Y47/bundle.json","state":"https://pith.science/pith/6R25VUJ7AMEXHXO5TYXYLJ2Y47/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6R25VUJ7AMEXHXO5TYXYLJ2Y47/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:6R25VUJ7AMEXHXO5TYXYLJ2Y47","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":"8d1774501a6a522a25769eda6acb4f4af687fc8674a5a4a564ab712ec91af3be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T15:57:58Z","title_canon_sha256":"14142370df77e2bf28cfaeb11b2e53f1e283ea4c6a14d64f1ac974e434933825"},"schema_version":"1.0","source":{"id":"2212.00603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.00603","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"arxiv_version","alias_value":"2212.00603v1","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00603","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"pith_short_12","alias_value":"6R25VUJ7AMEX","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"pith_short_16","alias_value":"6R25VUJ7AMEXHXO5","created_at":"2026-07-05T05:21:36Z"},{"alias_kind":"pith_short_8","alias_value":"6R25VUJ7","created_at":"2026-07-05T05:21:36Z"}],"graph_snapshots":[{"event_id":"sha256:354c745de3df11dd48739474639b821873c70fd328b2d88cbfbbc74d4a61e423","target":"graph","created_at":"2026-07-05T05:21:36Z","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/2212.00603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work considers the sample complexity of obtaining an $\\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating, we prove an upper bound of $\\widetilde O(H \\varepsilon^{-3} \\ln \\frac{1}{\\delta})$ samples per state-action pair, where $H := sp(h^*)$ is the span of bias of any optimal policy, $\\varepsilon$ is the accuracy and $\\delta$ is the failure probability. This bound improves the best-known mixing-time-based approaches in [Jin & Sidford 2021], which assume the mixing","authors_text":"Jinghan Wang, Lin F. Yang, Mengdi Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T15:57:58Z","title":"Near Sample-Optimal Reduction-based Policy Learning for Average Reward MDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00603","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:bd333b9b2eb980b040447488ef539a38ddc253f6caa229a1503039ae7e891385","target":"record","created_at":"2026-07-05T05:21:36Z","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":"8d1774501a6a522a25769eda6acb4f4af687fc8674a5a4a564ab712ec91af3be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T15:57:58Z","title_canon_sha256":"14142370df77e2bf28cfaeb11b2e53f1e283ea4c6a14d64f1ac974e434933825"},"schema_version":"1.0","source":{"id":"2212.00603","kind":"arxiv","version":1}},"canonical_sha256":"f475dad13f030973dddd9e2f85a758e7c069e38861ac5a117780d979c69d58a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f475dad13f030973dddd9e2f85a758e7c069e38861ac5a117780d979c69d58a3","first_computed_at":"2026-07-05T05:21:36.022658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:36.022658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9bEb9nuHxsWQ84FWjSwFgbJYE91/Xut7oT8pjxKUFH39mvhZtwoGzRpoZjrn7Dtr/So/A3+GKFwooxR50PZpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:36.022998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.00603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd333b9b2eb980b040447488ef539a38ddc253f6caa229a1503039ae7e891385","sha256:354c745de3df11dd48739474639b821873c70fd328b2d88cbfbbc74d4a61e423"],"state_sha256":"54cbbc22d765b42ef3d3090f24febd8e1ace7811665caec6ad71b197c052d412"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cqCNFxbkXJOgG1jVqpDqWg9zJEz1z0YPjuqG3z0O6JxDCWkIt1M3HhtEULoXSbrRjEmpKCPqm5KKlMIaJ4Y1AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:33:36.813366Z","bundle_sha256":"c4ce942b7db6725c947b60a9a2c44b837fb88f7fdc2ba7b70bfc2ae71b18ada1"}}