{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XU2APM24WIX6XLIHWLD6A2TWY7","short_pith_number":"pith:XU2APM24","schema_version":"1.0","canonical_sha256":"bd3407b35cb22febad07b2c7e06a76c7cb8c5238b4cf8f93df5cb30d15880a00","source":{"kind":"arxiv","id":"2606.28669","version":1},"attestation_state":"computed","paper":{"title":"Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Congde Hu, Danping Li, Lin Xu, Zhuo Jin","submitted_at":"2026-06-27T01:03:53Z","abstract_excerpt":"To address parameter misspecification and sudden structural environmental changes in conventional stochastic differential game (SDG) frameworks, this paper introduces a distributional control approach that characterizes optimal strategies as probability distributions over actions, conditioned on the continuous state, the discrete regime state, and parameters. This forms a reinforcement learning framework for entropy-regularized zero-sum stochastic differential games (ERRL-ZSSDGs) in a regime-switching jump-diffusion process. Using the dynamic programming principle (DPP), we derive the associat"},"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":"2606.28669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-27T01:03:53Z","cross_cats_sorted":[],"title_canon_sha256":"ed206a99f1c3b8773c166031bbbd89b35684e8a59c39c3cb3c3576aeec4ed808","abstract_canon_sha256":"a4849092314fe67a4b8ddf446e6c792d32fd3f65227f539343f1283dd1ddbdb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:46.786824Z","signature_b64":"WO97PFociQnOJQvHneXEYnpy6RhSDN8LfvUnl3clrAnpaug3yWmzAkLQfmR3l2dob1wWTKJgjVds/aLSNmtfAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd3407b35cb22febad07b2c7e06a76c7cb8c5238b4cf8f93df5cb30d15880a00","last_reissued_at":"2026-06-30T01:16:46.785909Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:46.785909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropy Regularized Reinforcement Learning for Zero-Sum Stochastic Differential Games in a Regime-Switching Jump-Diffusion Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Congde Hu, Danping Li, Lin Xu, Zhuo Jin","submitted_at":"2026-06-27T01:03:53Z","abstract_excerpt":"To address parameter misspecification and sudden structural environmental changes in conventional stochastic differential game (SDG) frameworks, this paper introduces a distributional control approach that characterizes optimal strategies as probability distributions over actions, conditioned on the continuous state, the discrete regime state, and parameters. This forms a reinforcement learning framework for entropy-regularized zero-sum stochastic differential games (ERRL-ZSSDGs) in a regime-switching jump-diffusion process. Using the dynamic programming principle (DPP), we derive the associat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28669","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/2606.28669/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":"2606.28669","created_at":"2026-06-30T01:16:46.786012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28669v1","created_at":"2026-06-30T01:16:46.786012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28669","created_at":"2026-06-30T01:16:46.786012+00:00"},{"alias_kind":"pith_short_12","alias_value":"XU2APM24WIX6","created_at":"2026-06-30T01:16:46.786012+00:00"},{"alias_kind":"pith_short_16","alias_value":"XU2APM24WIX6XLIH","created_at":"2026-06-30T01:16:46.786012+00:00"},{"alias_kind":"pith_short_8","alias_value":"XU2APM24","created_at":"2026-06-30T01:16:46.786012+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/XU2APM24WIX6XLIHWLD6A2TWY7","json":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7.json","graph_json":"https://pith.science/api/pith-number/XU2APM24WIX6XLIHWLD6A2TWY7/graph.json","events_json":"https://pith.science/api/pith-number/XU2APM24WIX6XLIHWLD6A2TWY7/events.json","paper":"https://pith.science/paper/XU2APM24"},"agent_actions":{"view_html":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7","download_json":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7.json","view_paper":"https://pith.science/paper/XU2APM24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28669&json=true","fetch_graph":"https://pith.science/api/pith-number/XU2APM24WIX6XLIHWLD6A2TWY7/graph.json","fetch_events":"https://pith.science/api/pith-number/XU2APM24WIX6XLIHWLD6A2TWY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7/action/storage_attestation","attest_author":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7/action/author_attestation","sign_citation":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7/action/citation_signature","submit_replication":"https://pith.science/pith/XU2APM24WIX6XLIHWLD6A2TWY7/action/replication_record"}},"created_at":"2026-06-30T01:16:46.786012+00:00","updated_at":"2026-06-30T01:16:46.786012+00:00"}