{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FZOY3UOXG2VMSO7HWKNTOFLWWP","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":"50afb8906a8fecb52384f2cee99373088fb2750ba252ed0bbd20bf4e8196d5b9","cross_cats_sorted":["cs.LG","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-05-30T17:02:18Z","title_canon_sha256":"f43f3a91ccc09fbadc123a0dbf70c27723af5f6e5dacd7745d3b90aed53bfb2e"},"schema_version":"1.0","source":{"id":"2405.20250","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20250","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20250v3","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20250","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"pith_short_12","alias_value":"FZOY3UOXG2VM","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"pith_short_16","alias_value":"FZOY3UOXG2VMSO7H","created_at":"2026-07-05T10:38:20Z"},{"alias_kind":"pith_short_8","alias_value":"FZOY3UOX","created_at":"2026-07-05T10:38:20Z"}],"graph_snapshots":[{"event_id":"sha256:8c6bb83af9c067fa22a9e4772a4dd3ff92618cf4c0b986cc7a6f3132b13ec38c","target":"graph","created_at":"2026-07-05T10:38:20Z","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/2405.20250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Entropy regularization has been widely used in policy optimization algorithms to enhance exploration and the robustness of the optimal control; however it also introduces an additional regularization bias. This work quantifies the impact of entropy regularization on the convergence of policy gradient methods for stochastic exit time control problems. We analyze a continuous-time policy mirror descent dynamics, which updates the policy based on the gradient of an entropy-regularized value function and adjusts the strength of entropy regularization as the algorithm progresses. We prove that with","authors_text":"David \\v{S}i\\v{s}ka, Deven Sethi, Yufei Zhang","cross_cats":["cs.LG","math.PR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-05-30T17:02:18Z","title":"Entropy annealing for policy mirror descent in continuous time and space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20250","kind":"arxiv","version":3},"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":"sha256:211db9ae2368fb46ca1d3d5986790f7701c104d56ffd46db0b679b30f0c1ee70","target":"record","created_at":"2026-07-05T10:38:20Z","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":"50afb8906a8fecb52384f2cee99373088fb2750ba252ed0bbd20bf4e8196d5b9","cross_cats_sorted":["cs.LG","math.PR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-05-30T17:02:18Z","title_canon_sha256":"f43f3a91ccc09fbadc123a0dbf70c27723af5f6e5dacd7745d3b90aed53bfb2e"},"schema_version":"1.0","source":{"id":"2405.20250","kind":"arxiv","version":3}},"canonical_sha256":"2e5d8dd1d736aac93be7b29b371576b3e4e447f259cd502725716adda4fa7094","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e5d8dd1d736aac93be7b29b371576b3e4e447f259cd502725716adda4fa7094","first_computed_at":"2026-07-05T10:38:20.905533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:20.905533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lE7YhlX9aLXcgBJpOvsxCGrxAzkWObRnVg0UupAEs5mJMPGE4e0kOkV1kx01GWXtXpzcFpk5l1vJygQR4MQ6Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:20.905988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20250","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:211db9ae2368fb46ca1d3d5986790f7701c104d56ffd46db0b679b30f0c1ee70","sha256:8c6bb83af9c067fa22a9e4772a4dd3ff92618cf4c0b986cc7a6f3132b13ec38c"],"state_sha256":"4d79f69fbe8ed5886117963d829afc21e7562238df71ce160520bec3dfe99862"}