{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4S4DSWAJ54C76BHRN6BALYA7PX","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":"082b4d0b27baf29170df642156d69c2f0795eeefd140f6c681d15dbf9c4775ec","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T10:15:00Z","title_canon_sha256":"6a30b38d669b318047f090a56cc4f3e1e150da1914dd93ca69e6665362bf0f39"},"schema_version":"1.0","source":{"id":"2205.11168","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.11168","created_at":"2026-07-05T08:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2205.11168v4","created_at":"2026-07-05T08:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11168","created_at":"2026-07-05T08:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"4S4DSWAJ54C7","created_at":"2026-07-05T08:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"4S4DSWAJ54C76BHR","created_at":"2026-07-05T08:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"4S4DSWAJ","created_at":"2026-07-05T08:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:4dc0c8f01a5253f75279bb2d23c8063f7d42f307a3ce75b8282246a5b806d8d5","target":"graph","created_at":"2026-07-05T08:38:50Z","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/2205.11168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider reinforcement learning for continuous-time Markov decision processes (MDPs) in the infinite-horizon, average-reward setting. In contrast to discrete-time MDPs, a continuous-time process moves to a state and stays there for a random holding time after an action is taken. With unknown transition probabilities and rates of exponential holding times, we derive instance-dependent regret lower bounds that are logarithmic in the time horizon. Moreover, we design a learning algorithm and establish a finite-time regret bound that achieves the logarithmic growth rate. Our analysis builds upo","authors_text":"Xuefeng Gao, Xun Yu Zhou","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T10:15:00Z","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11168","kind":"arxiv","version":4},"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":"sha256:9e30c0476dff00b6071f54c96280af2d115de524ad581a60b03d048585f5d642","target":"record","created_at":"2026-07-05T08:38:50Z","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":"082b4d0b27baf29170df642156d69c2f0795eeefd140f6c681d15dbf9c4775ec","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T10:15:00Z","title_canon_sha256":"6a30b38d669b318047f090a56cc4f3e1e150da1914dd93ca69e6665362bf0f39"},"schema_version":"1.0","source":{"id":"2205.11168","kind":"arxiv","version":4}},"canonical_sha256":"e4b8395809ef05ff04f16f8205e01f7dec5311f3df843f773832ce430d576006","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4b8395809ef05ff04f16f8205e01f7dec5311f3df843f773832ce430d576006","first_computed_at":"2026-07-05T08:38:50.427912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:50.427912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UgCv9wTkQF0OfS+fihon/mTsufIUXD7jZectGCNi3HDuDiNVm81L8Gy/uOXi+OFnG/SmDKYnnRse5gAsaIhhDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:50.428465Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.11168","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e30c0476dff00b6071f54c96280af2d115de524ad581a60b03d048585f5d642","sha256:4dc0c8f01a5253f75279bb2d23c8063f7d42f307a3ce75b8282246a5b806d8d5"],"state_sha256":"58be2f0afbb86d481e06fb927ca653712890092d10ddc44d7ad78bc6c6a2f1d1"}