{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GY3U4XPXCXGATWWOYN3W3F57RZ","short_pith_number":"pith:GY3U4XPX","schema_version":"1.0","canonical_sha256":"36374e5df715cc09dacec3776d97bf8e73ab6f53fb922dfbeda51988c565e44f","source":{"kind":"arxiv","id":"2502.04788","version":1},"attestation_state":"computed","paper":{"title":"A non-zero-sum game with reinforcement learning under mean-variance framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hao Wang, Junyi Guo, Kam Chuen Yuen, Xia Han","submitted_at":"2025-02-07T09:48:39Z","abstract_excerpt":"In this paper, we investigate a competitive market involving two agents who consider both their own wealth and the wealth gap with their opponent. Both agents can invest in a financial market consisting of a risk-free asset and a risky asset, under conditions where model parameters are partially or completely unknown. This setup gives rise to a non-zero-sum differential game within the framework of reinforcement learning (RL). Each agent aims to maximize his own Choquet-regularized, time-inconsistent mean-variance objective. Adopting the dynamic programming approach, we derive a time-consisten"},"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":"2502.04788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-07T09:48:39Z","cross_cats_sorted":[],"title_canon_sha256":"5201cbe43505ff2c91d9145871f56ff59714d0c9114a65693c02dd94b7984741","abstract_canon_sha256":"b598d163eb536a01c7febff959d96c6df69334c824cb0907ee704c2b5e7040c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:57.315523Z","signature_b64":"qSjHCQFwqDcFMaB//i+FRX5sgc8eLShKyI2G0RHSKfchlFZAn4FhhU2Fov/peyXP7jb8Gl4veOfDrz3j32HiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36374e5df715cc09dacec3776d97bf8e73ab6f53fb922dfbeda51988c565e44f","last_reissued_at":"2026-07-05T10:10:57.314977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:57.314977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A non-zero-sum game with reinforcement learning under mean-variance framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hao Wang, Junyi Guo, Kam Chuen Yuen, Xia Han","submitted_at":"2025-02-07T09:48:39Z","abstract_excerpt":"In this paper, we investigate a competitive market involving two agents who consider both their own wealth and the wealth gap with their opponent. Both agents can invest in a financial market consisting of a risk-free asset and a risky asset, under conditions where model parameters are partially or completely unknown. This setup gives rise to a non-zero-sum differential game within the framework of reinforcement learning (RL). Each agent aims to maximize his own Choquet-regularized, time-inconsistent mean-variance objective. Adopting the dynamic programming approach, we derive a time-consisten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04788","kind":"arxiv","version":1},"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/2502.04788/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":"2502.04788","created_at":"2026-07-05T10:10:57.315035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04788v1","created_at":"2026-07-05T10:10:57.315035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04788","created_at":"2026-07-05T10:10:57.315035+00:00"},{"alias_kind":"pith_short_12","alias_value":"GY3U4XPXCXGA","created_at":"2026-07-05T10:10:57.315035+00:00"},{"alias_kind":"pith_short_16","alias_value":"GY3U4XPXCXGATWWO","created_at":"2026-07-05T10:10:57.315035+00:00"},{"alias_kind":"pith_short_8","alias_value":"GY3U4XPX","created_at":"2026-07-05T10:10:57.315035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ","json":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ.json","graph_json":"https://pith.science/api/pith-number/GY3U4XPXCXGATWWOYN3W3F57RZ/graph.json","events_json":"https://pith.science/api/pith-number/GY3U4XPXCXGATWWOYN3W3F57RZ/events.json","paper":"https://pith.science/paper/GY3U4XPX"},"agent_actions":{"view_html":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ","download_json":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ.json","view_paper":"https://pith.science/paper/GY3U4XPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04788&json=true","fetch_graph":"https://pith.science/api/pith-number/GY3U4XPXCXGATWWOYN3W3F57RZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GY3U4XPXCXGATWWOYN3W3F57RZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ/action/storage_attestation","attest_author":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ/action/author_attestation","sign_citation":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ/action/citation_signature","submit_replication":"https://pith.science/pith/GY3U4XPXCXGATWWOYN3W3F57RZ/action/replication_record"}},"created_at":"2026-07-05T10:10:57.315035+00:00","updated_at":"2026-07-05T10:10:57.315035+00:00"}