{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:33N6USFMRMMWSSOIPGBNJFMFCL","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":"9ae81bdab43c5d976e9360e9cbc303ac431b3245d89a7c6fa132294e65fdf7ec","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2026-06-10T08:31:54Z","title_canon_sha256":"7ff7a7f9df33de0c6bdc3e84485e9a7636676888a966dc29ea39b615b867444e"},"schema_version":"1.0","source":{"id":"2606.11798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11798","created_at":"2026-06-11T01:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11798v1","created_at":"2026-06-11T01:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11798","created_at":"2026-06-11T01:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"33N6USFMRMMW","created_at":"2026-06-11T01:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"33N6USFMRMMWSSOI","created_at":"2026-06-11T01:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"33N6USFM","created_at":"2026-06-11T01:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:fdc7e2ba0e8f5d3812301403eeb68e5c915cb7a0dfd5a4f4001447dcabe662e8","target":"graph","created_at":"2026-06-11T01:10:08Z","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/2606.11798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we develop a continuous-time model-free reinforcement learning algorithm to learn deterministic equilibrium policies in general time-inconsistent control problems. Utilizing the extended Hamilton-Jacobi-Bellman system, we recast the original time-inconsistent problem into an equivalent two-stage problem. In the first stage, for given auxiliary functions, we employ the deterministic policy gradient approach to learn an optimal policy in an auxiliary time-consistent control problem. In the second stage, given the updated policy, we exploit the inner fixed point iterations and some","authors_text":"Xiang Yu, Xin Guo, Yijie Huang","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2026-06-10T08:31:54Z","title":"Deterministic Policy Gradient for Learning Equilibrium in Time-Inconsistent Control Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11798","kind":"arxiv","version":1},"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:d83721cfd6e75abe06c90b4c62966809beaa6d932faff751d431280e29451823","target":"record","created_at":"2026-06-11T01:10:08Z","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":"9ae81bdab43c5d976e9360e9cbc303ac431b3245d89a7c6fa132294e65fdf7ec","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.CP","submitted_at":"2026-06-10T08:31:54Z","title_canon_sha256":"7ff7a7f9df33de0c6bdc3e84485e9a7636676888a966dc29ea39b615b867444e"},"schema_version":"1.0","source":{"id":"2606.11798","kind":"arxiv","version":1}},"canonical_sha256":"dedbea48ac8b196949c87982d4958512fedd783bd6dd1c3a26610eee9fbb2845","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dedbea48ac8b196949c87982d4958512fedd783bd6dd1c3a26610eee9fbb2845","first_computed_at":"2026-06-11T01:10:08.555303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:08.555303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AswIDMTFKE/w0MKsXp9YvRwVaC1o3zY5IBaGqV6FcZ6IA+9VXsZiorjfq5KkFzo9vnDUb1FvYjQznZCa8XfiBw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:08.556215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d83721cfd6e75abe06c90b4c62966809beaa6d932faff751d431280e29451823","sha256:fdc7e2ba0e8f5d3812301403eeb68e5c915cb7a0dfd5a4f4001447dcabe662e8"],"state_sha256":"f3dc0405c77bf6c1f22d1f353b4f0aa67e277c8c8e0c4cd6e93fe478464316ae"}