{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZCVZIOXALTXE3BLDU4NWNOWOJ4","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":"830565cf23fce4613fb81e2d6bcf04b77a035b7089f1d5861f7b20360b186c66","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:04:59Z","title_canon_sha256":"03845fc45ceec497163534ed0e97652299513e483cff184f975b34cbf0f568a5"},"schema_version":"1.0","source":{"id":"2605.13639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13639","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13639v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13639","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZCVZIOXALTXE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZCVZIOXALTXE3BLD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZCVZIOXA","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fbf2884076af6be24283084d0e2ae8cf9dcb32a99858c42f1d2e03d0aa9c8018","target":"graph","created_at":"2026-05-18T02:44:17Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we prove the first Õ(ε^{-2}) sample complexity guarantee for finding an ε-optimal policy under minimal assumptions, namely, the existence of a policy that induces an irreducible Markov chain."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"the existence of a policy that induces an irreducible Markov chain; the coupled Lyapunov drift framework and cross-domination property hold for the single-loop off-policy updates with unbounded iterates."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Single-loop actor-critic achieves the first Õ(ε^{-2}) sample complexity for ε-optimal policies under minimal irreducibility assumptions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Single-loop off-policy actor-critic reaches an ε-optimal policy with Õ(ε^{-2}) samples under only irreducibility of one policy."}],"snapshot_sha256":"2764f336ed3c3a0b4e7ff72df631b4b0848a072dc16277b58f4dc2b03c6a1332"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In this paper, we establish last-iterate convergence rates for off-policy actor--critic methods in reinforcement learning. In particular, under a single-loop, single-timescale implementation and a broad class of policy updates, including approximate policy iteration and natural policy gradient methods, we prove the first $\\tilde{\\mathcal{O}}(\\epsilon^{-2})$ sample complexity guarantee for finding an $\\epsilon$-optimal policy under minimal assumptions, namely, the existence of a policy that induces an irreducible Markov chain. This stands in stark contrast to the existing literature, where an $","authors_text":"Ishaq Hamza, Zaiwei Chen","cross_cats":["math.OC","stat.ML"],"headline":"Single-loop off-policy actor-critic reaches an ε-optimal policy with Õ(ε^{-2}) samples under only irreducibility of one policy.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:04:59Z","title":"Achieving $\\epsilon^{-2}$ Sample Complexity for Single-Loop Actor-Critic under Minimal Assumptions"},"references":{"count":69,"internal_anchors":2,"resolved_work":69,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Agarwal, A., Kakade, S. M., Lee, J. D., and Mahajan, G. (2021). On the theory of policy gra- dient methods: Optimality, approximation, and distribution shift.Journal of Machine Learning Research, 22(9","work_id":"7944bdec-08fb-439b-b740-79e2cdc97ec4","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Alacaoglu, A., Viano, L., He, N., and Cevher, V. (2022). A natural actor-critic framework for zero-sum Markov games. InInternational Conference on Machine Learning, pages 307–366. PMLR","work_id":"6178018b-2f46-42b6-bd4b-65915ad3a72e","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Banach, S. (1922). Sur les op´ erations dans les ensembles abstraits et leur application aux ´ equations int´ egrales.Fund. Math, 3(1):133–181","work_id":"d0013531-a137-453f-a361-27c18c3e4832","year":1922},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Bertsekas, D. P. (2011). Approximate policy iteration: A survey and some new methods. Journal of Control Theory and Applications, 9(3):310–335","work_id":"945f2728-8995-4602-802d-7e28f5155c45","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Bhandari, J., Russo, D., and Singal, R. (2018). A finite-time analysis of temporal difference learning with linear function approximation. InConference On Learning Theory, pages 1691– 1692","work_id":"7c3c5f71-b5c6-4b83-8aa0-5e1c86e122cc","year":2018}],"snapshot_sha256":"04e9775dddc6aa50f92f8fe99f3feb5bbadf9052abd3fc8c100cdb3221c1efa9"},"source":{"id":"2605.13639","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:24:50.031010Z","id":"c0707b4f-6d5f-4e58-92c0-e19ce0fe564c","model_set":{"reader":"grok-4.3"},"one_line_summary":"Single-loop actor-critic achieves the first Õ(ε^{-2}) sample complexity for ε-optimal policies under minimal irreducibility assumptions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Single-loop off-policy actor-critic reaches an ε-optimal policy with Õ(ε^{-2}) samples under only irreducibility of one policy.","strongest_claim":"we prove the first Õ(ε^{-2}) sample complexity guarantee for finding an ε-optimal policy under minimal assumptions, namely, the existence of a policy that induces an irreducible Markov chain.","weakest_assumption":"the existence of a policy that induces an irreducible Markov chain; the coupled Lyapunov drift framework and cross-domination property hold for the single-loop off-policy updates with unbounded iterates."}},"verdict_id":"c0707b4f-6d5f-4e58-92c0-e19ce0fe564c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7e6e1e5d4b0ca16023133cc6c92065c254da8e6d56512eb15af75a02c07a8833","target":"record","created_at":"2026-05-18T02:44:17Z","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":"830565cf23fce4613fb81e2d6bcf04b77a035b7089f1d5861f7b20360b186c66","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:04:59Z","title_canon_sha256":"03845fc45ceec497163534ed0e97652299513e483cff184f975b34cbf0f568a5"},"schema_version":"1.0","source":{"id":"2605.13639","kind":"arxiv","version":1}},"canonical_sha256":"c8ab943ae05cee4d8563a71b66bace4f214166effee64669864687fd34d7d3c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8ab943ae05cee4d8563a71b66bace4f214166effee64669864687fd34d7d3c3","first_computed_at":"2026-05-18T02:44:17.625374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:17.625374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LMxOfnSR2r+kigztl53Vrd5v4v4w5c2iYdYU17UeQDbfacpE+KGiq/RHOUXlG2QZ11UYwy+jbyZ3rhmj97GWBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:17.625801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e6e1e5d4b0ca16023133cc6c92065c254da8e6d56512eb15af75a02c07a8833","sha256:fbf2884076af6be24283084d0e2ae8cf9dcb32a99858c42f1d2e03d0aa9c8018"],"state_sha256":"520c141a284fa9f0a2814927e3dd1544d59cd38bf9a4586ec9af0c27359a195d"}