{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KRNSQT3KGOZU5HCQDMQ6EQP3DR","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":"e24d3bd2819aadd2e961f11695e5a71ef60f951b88f29eaa833cad166d82727c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T19:39:24Z","title_canon_sha256":"cb6ea5349fd5f2689aa6051266a82d666e74c0c0777b1a70b09007b42bac655d"},"schema_version":"1.0","source":{"id":"2205.14211","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.14211","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"arxiv_version","alias_value":"2205.14211v1","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14211","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_12","alias_value":"KRNSQT3KGOZU","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_16","alias_value":"KRNSQT3KGOZU5HCQ","created_at":"2026-07-05T04:27:15Z"},{"alias_kind":"pith_short_8","alias_value":"KRNSQT3K","created_at":"2026-07-05T04:27:15Z"}],"graph_snapshots":[{"event_id":"sha256:51bcc21ebfd3f5527fc8c8f994bd930e98bc6a97a0a33c979a3a9532b57bd984","target":"graph","created_at":"2026-07-05T04:27:15Z","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/2205.14211/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we consider and analyze the sample complexity of model-free reinforcement learning with a generative model. Particularly, we analyze mirror descent value iteration (MDVI) by Geist et al. (2019) and Vieillard et al. (2020a), which uses the Kullback-Leibler divergence and entropy regularization in its value and policy updates. Our analysis shows that it is nearly minimax-optimal for finding an $\\varepsilon$-optimal policy when $\\varepsilon$ is sufficiently small. This is the first theoretical result that demonstrates that a simple model-free algorithm without variance-reduction can","authors_text":"Csaba Szepesv\\'ari, Jincheng Mei, Matthieu Geist, Michal Valko, Mohammad Gheshlaghi Azar, Nino Vieillard, Olivier Pietquin, Pierre M\\'enard, R\\'emi Munos, Tadashi Kozuno, Toshinori Kitamura, Wenhao Yang, Yunhao Tang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T19:39:24Z","title":"KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14211","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:f6e4ea40fba6f3ff9865df1f9dafe19c5960ffda70db37a2bc9c317a9de9dc7e","target":"record","created_at":"2026-07-05T04:27:15Z","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":"e24d3bd2819aadd2e961f11695e5a71ef60f951b88f29eaa833cad166d82727c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-27T19:39:24Z","title_canon_sha256":"cb6ea5349fd5f2689aa6051266a82d666e74c0c0777b1a70b09007b42bac655d"},"schema_version":"1.0","source":{"id":"2205.14211","kind":"arxiv","version":1}},"canonical_sha256":"545b284f6a33b34e9c501b21e241fb1c78babf5b8167d6177600bd1074b4cdc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"545b284f6a33b34e9c501b21e241fb1c78babf5b8167d6177600bd1074b4cdc6","first_computed_at":"2026-07-05T04:27:15.101547Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:15.101547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rQX/WxxP/SBaZp0qQXmHWCdQrgvvBwtwDjme2pxb8PbNjJFOsoCIntpg8NAmYz1i7noQFIINEujc2/BVlpVSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:15.102016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.14211","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6e4ea40fba6f3ff9865df1f9dafe19c5960ffda70db37a2bc9c317a9de9dc7e","sha256:51bcc21ebfd3f5527fc8c8f994bd930e98bc6a97a0a33c979a3a9532b57bd984"],"state_sha256":"545bab182169784ce0499693313c7bdaf60b293702111c3b26b5247f354c6fdd"}