{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DZCZS6GJO5UHKOSQ5WCVPN3G6N","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":"d28bcd43a6b8d2d49d1a346e82050c1d454f300e8df3734081937c9d0fe03a8f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","title_canon_sha256":"275ed3111c7949a375887d06e6e2535b719d2cdc4ec468f4dc2c3d02c1fe7eaa"},"schema_version":"1.0","source":{"id":"2505.03710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03710","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03710v1","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03710","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"DZCZS6GJO5UH","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"DZCZS6GJO5UHKOSQ","created_at":"2026-07-05T10:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"DZCZS6GJ","created_at":"2026-07-05T10:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:481e5ffca9bfe8d11456bb1e1d8b1db8d82f56a41f33823454ceabd1e1fea64a","target":"graph","created_at":"2026-07-05T10:59:20Z","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/2505.03710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work has successfully learned an $\\epsilon$-optimal policy with a sample complexity of $O(1/\\epsilon^2)$ trajectories with general function approximation when strategic exploration is necessary.\n  We address this open problem by introducing a novel actor-critic algorithm that attains a sample-complexity of $O(dH^5 \\log|\\mathcal{A}|/\\epsilon^2 + d H^4 \\log|\\mathc","authors_text":"Kevin Tan, Wei Fan, Yuting Wei","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","title":"Actor-Critics Can Achieve Optimal Sample Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03710","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":"sha256:91ccb32085484d4a70e76944917f09b44f6fd49a211aafbd5f3f7b87c554fb32","target":"record","created_at":"2026-07-05T10:59:20Z","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":"d28bcd43a6b8d2d49d1a346e82050c1d454f300e8df3734081937c9d0fe03a8f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-06T17:32:39Z","title_canon_sha256":"275ed3111c7949a375887d06e6e2535b719d2cdc4ec468f4dc2c3d02c1fe7eaa"},"schema_version":"1.0","source":{"id":"2505.03710","kind":"arxiv","version":1}},"canonical_sha256":"1e459978c97768753a50ed8557b766f347daa99f651487caafce764a2e58f6d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e459978c97768753a50ed8557b766f347daa99f651487caafce764a2e58f6d2","first_computed_at":"2026-07-05T10:59:20.849144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:20.849144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hMoZryj6biCCjRxyhGykruko0MgsBXUBuptXNqs3xGBkLDJ+fVw1dOZ7zwIQDbMrBVXVBGh8lmFHKd5Cf5CkDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:20.849632Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91ccb32085484d4a70e76944917f09b44f6fd49a211aafbd5f3f7b87c554fb32","sha256:481e5ffca9bfe8d11456bb1e1d8b1db8d82f56a41f33823454ceabd1e1fea64a"],"state_sha256":"c4e3282206479bc834853f1b509c8a59930db64b1805a9c0ece84ac7b350d4be"}