{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YJ6I6UYLZCH2MWUNPSAXZZDOZ5","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":"4991c51d5b974b4dc3d8483a86051af27416d7c4fad226c5c3316f99589ca7aa","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T22:27:57Z","title_canon_sha256":"8c78ee9bba21ddf364436b41d110d1dfa6482010288e88b2ea52dd237f336841"},"schema_version":"1.0","source":{"id":"2506.00286","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00286","created_at":"2026-05-20T01:04:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00286v3","created_at":"2026-05-20T01:04:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00286","created_at":"2026-05-20T01:04:54Z"},{"alias_kind":"pith_short_12","alias_value":"YJ6I6UYLZCH2","created_at":"2026-05-20T01:04:54Z"},{"alias_kind":"pith_short_16","alias_value":"YJ6I6UYLZCH2MWUN","created_at":"2026-05-20T01:04:54Z"},{"alias_kind":"pith_short_8","alias_value":"YJ6I6UYL","created_at":"2026-05-20T01:04:54Z"}],"graph_snapshots":[{"event_id":"sha256:c80d5b2f7a530b3a03ac8aadc671dc717fc2bfdb79b91e6390c8786ef898479f","target":"graph","created_at":"2026-05-20T01:04:54Z","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/2506.00286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter $\\beta \\neq 0$ controls the agent's risk attitude: $\\beta>0$ for risk-averse and $\\beta<0$ for risk-seeking behavior. A generative model of the MDP is assumed to be available. Our focus is on the sample complexities of learning the optimal state-action value function (value learning) and an optimal policy (policy learning) under recursive ERM. We introduce a model-based algorithm, called Model-Based ERM $Q$-Value Iteration (MB-RS-QVI), and derive PAC-ty","authors_text":"Mohammad Sadegh Talebi, Oliver Mortensen","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T22:27:57Z","title":"Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00286","kind":"arxiv","version":3},"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":"sha256:424af24eee93d862408f5f4846d0c43fb6aa591f5e67950d8a7280e1748841b0","target":"record","created_at":"2026-05-20T01:04:54Z","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":"4991c51d5b974b4dc3d8483a86051af27416d7c4fad226c5c3316f99589ca7aa","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-30T22:27:57Z","title_canon_sha256":"8c78ee9bba21ddf364436b41d110d1dfa6482010288e88b2ea52dd237f336841"},"schema_version":"1.0","source":{"id":"2506.00286","kind":"arxiv","version":3}},"canonical_sha256":"c27c8f530bc88fa65a8d7c817ce46ecf45b6c2ab6490c106aa4efe7e603af8b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c27c8f530bc88fa65a8d7c817ce46ecf45b6c2ab6490c106aa4efe7e603af8b9","first_computed_at":"2026-05-20T01:04:54.515290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:04:54.515290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CrQaiiAN8kc6q9X0YWx/TU+TcimQC7SA4ayhUAxaU89cq9TKbPm3auZPHgIw4Cq4D0KRmQkDd+NIfJQcCTvCCA==","signature_status":"signed_v1","signed_at":"2026-05-20T01:04:54.516232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00286","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:424af24eee93d862408f5f4846d0c43fb6aa591f5e67950d8a7280e1748841b0","sha256:c80d5b2f7a530b3a03ac8aadc671dc717fc2bfdb79b91e6390c8786ef898479f"],"state_sha256":"ee0d042dca492a1e51c4459973ab5b91b53d5628a4467c692e465d20af8ccb71"}