{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2OAHHCVBWBLNLW2DKOOXNR2A6G","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":"4f803f0501b394bd7477e8eff73c3d931a89fddc6748c11515e49930f10966ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-27T17:11:06Z","title_canon_sha256":"4a601354975f1b80c5da565925eb57cc2dac0d745ccd4b056272757bdbeb8d32"},"schema_version":"1.0","source":{"id":"2004.12956","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12956","created_at":"2026-07-05T02:14:41Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12956v4","created_at":"2026-07-05T02:14:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12956","created_at":"2026-07-05T02:14:41Z"},{"alias_kind":"pith_short_12","alias_value":"2OAHHCVBWBLN","created_at":"2026-07-05T02:14:41Z"},{"alias_kind":"pith_short_16","alias_value":"2OAHHCVBWBLNLW2D","created_at":"2026-07-05T02:14:41Z"},{"alias_kind":"pith_short_8","alias_value":"2OAHHCVB","created_at":"2026-07-05T02:14:41Z"}],"graph_snapshots":[{"event_id":"sha256:0c742a8909701aeb9e94e4fd8151eb113c5782de2e682d13ab6fcb29236e824e","target":"graph","created_at":"2026-07-05T02:14:41Z","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/2004.12956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The actor-critic (AC) algorithm is a popular method to find an optimal policy in reinforcement learning. In the infinite horizon scenario, the finite-sample convergence rate for the AC and natural actor-critic (NAC) algorithms has been established recently, but under independent and identically distributed (i.i.d.) sampling and single-sample update at each iteration. In contrast, this paper characterizes the convergence rate and sample complexity of AC and NAC under Markovian sampling, with mini-batch data for each iteration, and with actor having general policy class approximation. We show th","authors_text":"Tengyu Xu, Yingbin Liang, Zhe Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-27T17:11:06Z","title":"Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12956","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:abf05e8bb831a298a2f47688f7c139dbb005dc501e401b6c0f79e59a2680be21","target":"record","created_at":"2026-07-05T02:14:41Z","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":"4f803f0501b394bd7477e8eff73c3d931a89fddc6748c11515e49930f10966ea","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-27T17:11:06Z","title_canon_sha256":"4a601354975f1b80c5da565925eb57cc2dac0d745ccd4b056272757bdbeb8d32"},"schema_version":"1.0","source":{"id":"2004.12956","kind":"arxiv","version":4}},"canonical_sha256":"d380738aa1b056d5db43539d76c740f18a72b5da053d818b713510efa5726335","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d380738aa1b056d5db43539d76c740f18a72b5da053d818b713510efa5726335","first_computed_at":"2026-07-05T02:14:41.529383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:41.529383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3a1tAx4g22/r7ZlJAJ3WiJ5TLRmaCwecBpSp3CNh2qWVAJ6lw33RJ8pEJzLeYMK0HarGZKCsJgMNbSLj+a9OBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:41.530136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.12956","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:abf05e8bb831a298a2f47688f7c139dbb005dc501e401b6c0f79e59a2680be21","sha256:0c742a8909701aeb9e94e4fd8151eb113c5782de2e682d13ab6fcb29236e824e"],"state_sha256":"acf25b0142c57ced3111d37801486243064db0c77b480b8a85e449a8216bbfb7"}