{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3FMKAPW2BZ3NXPEG4BRZJRZ366","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":"e6378f02af74a9b6cf370bea56cecb6bea7ef28f03e2acd260d18e7e4cb70c7d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-03T18:17:34Z","title_canon_sha256":"938e2f6f85eb437d0316ec623b458bd4710e5c85e09b4906e29f89a389c97d75"},"schema_version":"1.0","source":{"id":"2010.01404","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.01404","created_at":"2026-07-05T09:34:32Z"},{"alias_kind":"arxiv_version","alias_value":"2010.01404v4","created_at":"2026-07-05T09:34:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01404","created_at":"2026-07-05T09:34:32Z"},{"alias_kind":"pith_short_12","alias_value":"3FMKAPW2BZ3N","created_at":"2026-07-05T09:34:32Z"},{"alias_kind":"pith_short_16","alias_value":"3FMKAPW2BZ3NXPEG","created_at":"2026-07-05T09:34:32Z"},{"alias_kind":"pith_short_8","alias_value":"3FMKAPW2","created_at":"2026-07-05T09:34:32Z"}],"graph_snapshots":[{"event_id":"sha256:36b00ef584ee4113a38d3ab754d79ff4814dea88013445bff0e433090b009878","target":"graph","created_at":"2026-07-05T09:34:32Z","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/2010.01404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study investigates the mean-variance (MV) trade-off in reinforcement learning (RL), an instance of the sequential decision-making under uncertainty. Our objective is to obtain MV-efficient policies whose means and variances are located on the Pareto efficient frontier with respect to the MV trade-off; under the condition, any increase in the expected reward would necessitate a corresponding increase in variance, and vice versa. To this end, we propose a method that trains our policy to maximize the expected quadratic utility, defined as a weighted sum of the first and second moments of th","authors_text":"Kei Nakagawa, Kenshi Abe, Kentaro Baba, Masahiro Kato, Tetsuro Morimura","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-03T18:17:34Z","title":"Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01404","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:d624c85426c23e9a1d7a7c3e56c2f3fddb4cc5bf30a5e1104b48692a139aaa20","target":"record","created_at":"2026-07-05T09:34:32Z","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":"e6378f02af74a9b6cf370bea56cecb6bea7ef28f03e2acd260d18e7e4cb70c7d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-03T18:17:34Z","title_canon_sha256":"938e2f6f85eb437d0316ec623b458bd4710e5c85e09b4906e29f89a389c97d75"},"schema_version":"1.0","source":{"id":"2010.01404","kind":"arxiv","version":4}},"canonical_sha256":"d958a03eda0e76dbbc86e06394c73bf7be56a0228e0a5b840b20c8301b36cd82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d958a03eda0e76dbbc86e06394c73bf7be56a0228e0a5b840b20c8301b36cd82","first_computed_at":"2026-07-05T09:34:32.162714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:32.162714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kSQduiVqIqmgFWUb7TlacIMdMX9Gng73cFJpxsCdWJdwAirTZ+MAtbE+rTMoNEz2LC0jF0XmeOV/Gp5inaXuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:32.163165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.01404","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d624c85426c23e9a1d7a7c3e56c2f3fddb4cc5bf30a5e1104b48692a139aaa20","sha256:36b00ef584ee4113a38d3ab754d79ff4814dea88013445bff0e433090b009878"],"state_sha256":"0394380ec7c1f4be96df92ad7daa9b9c00d18b675c9291dcceff09d8c68377d6"}