{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3FMKAPW2BZ3NXPEG4BRZJRZ366","short_pith_number":"pith:3FMKAPW2","schema_version":"1.0","canonical_sha256":"d958a03eda0e76dbbc86e06394c73bf7be56a0228e0a5b840b20c8301b36cd82","source":{"kind":"arxiv","id":"2010.01404","version":4},"attestation_state":"computed","paper":{"title":"Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kei Nakagawa, Kenshi Abe, Kentaro Baba, Masahiro Kato, Tetsuro Morimura","submitted_at":"2020-10-03T18:17:34Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.01404","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-03T18:17:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"938e2f6f85eb437d0316ec623b458bd4710e5c85e09b4906e29f89a389c97d75","abstract_canon_sha256":"e6378f02af74a9b6cf370bea56cecb6bea7ef28f03e2acd260d18e7e4cb70c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:32.163165Z","signature_b64":"kSQduiVqIqmgFWUb7TlacIMdMX9Gng73cFJpxsCdWJdwAirTZ+MAtbE+rTMoNEz2LC0jF0XmeOV/Gp5inaXuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d958a03eda0e76dbbc86e06394c73bf7be56a0228e0a5b840b20c8301b36cd82","last_reissued_at":"2026-07-05T09:34:32.162714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:32.162714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean-Variance Efficient Reinforcement Learning with Applications to Dynamic Financial Investment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kei Nakagawa, Kenshi Abe, Kentaro Baba, Masahiro Kato, Tetsuro Morimura","submitted_at":"2020-10-03T18:17:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.01404","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.01404/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.01404","created_at":"2026-07-05T09:34:32.162772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.01404v4","created_at":"2026-07-05T09:34:32.162772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.01404","created_at":"2026-07-05T09:34:32.162772+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FMKAPW2BZ3N","created_at":"2026-07-05T09:34:32.162772+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FMKAPW2BZ3NXPEG","created_at":"2026-07-05T09:34:32.162772+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FMKAPW2","created_at":"2026-07-05T09:34:32.162772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10692","citing_title":"Continuous-time optimal investment with portfolio constraints: a reinforcement learning approach","ref_index":97,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366","json":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366.json","graph_json":"https://pith.science/api/pith-number/3FMKAPW2BZ3NXPEG4BRZJRZ366/graph.json","events_json":"https://pith.science/api/pith-number/3FMKAPW2BZ3NXPEG4BRZJRZ366/events.json","paper":"https://pith.science/paper/3FMKAPW2"},"agent_actions":{"view_html":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366","download_json":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366.json","view_paper":"https://pith.science/paper/3FMKAPW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.01404&json=true","fetch_graph":"https://pith.science/api/pith-number/3FMKAPW2BZ3NXPEG4BRZJRZ366/graph.json","fetch_events":"https://pith.science/api/pith-number/3FMKAPW2BZ3NXPEG4BRZJRZ366/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366/action/storage_attestation","attest_author":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366/action/author_attestation","sign_citation":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366/action/citation_signature","submit_replication":"https://pith.science/pith/3FMKAPW2BZ3NXPEG4BRZJRZ366/action/replication_record"}},"created_at":"2026-07-05T09:34:32.162772+00:00","updated_at":"2026-07-05T09:34:32.162772+00:00"}