{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QIRMDXTPKS6TPDF4PJT3NAZHOB","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":"daa6b6a60977c4323060fcd187328b3cd8cad9852f985631f9ae2a2fe3cd361f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-16T17:16:28Z","title_canon_sha256":"14d38c748939a8e8e2c492139202ff9f65d51bf3620edf6fcce85c4865f218df"},"schema_version":"1.0","source":{"id":"2510.14898","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14898","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14898v2","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14898","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"QIRMDXTPKS6T","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"QIRMDXTPKS6TPDF4","created_at":"2026-06-03T01:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"QIRMDXTP","created_at":"2026-06-03T01:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:82f217816d13bcb8d11e6a160e4aa115a974be7037fb9ae35f39d281fcd9fcbf","target":"graph","created_at":"2026-06-03T01:05:06Z","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/2510.14898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We prove the stability and global convergence of a coupled actor-critic gradient flow for infinite-horizon and entropy-regularised Markov decision processes (MDPs) in continuous state and action space with linear function approximation under Q-function realisability. We consider a version of the actor critic gradient flow where the critic is updated using temporal difference (TD) learning while the policy is updated using a policy mirror descent method on a separate timescale. For general action spaces, the relative entropy regularizer is unbounded and thus it is not clear a priori that the ac","authors_text":"David \\v{S}i\\v{s}ka, Denis Zorba, Lukasz Szpruch","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-16T17:16:28Z","title":"Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14898","kind":"arxiv","version":2},"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":"sha256:42b3b6aa284d129549213d487df09c1267f2fe295d7638ca0b08cfa9d484d105","target":"record","created_at":"2026-06-03T01:05:06Z","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":"daa6b6a60977c4323060fcd187328b3cd8cad9852f985631f9ae2a2fe3cd361f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-16T17:16:28Z","title_canon_sha256":"14d38c748939a8e8e2c492139202ff9f65d51bf3620edf6fcce85c4865f218df"},"schema_version":"1.0","source":{"id":"2510.14898","kind":"arxiv","version":2}},"canonical_sha256":"8222c1de6f54bd378cbc7a67b68327707772a0fe14563ea8e7b8e29290d02a6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8222c1de6f54bd378cbc7a67b68327707772a0fe14563ea8e7b8e29290d02a6e","first_computed_at":"2026-06-03T01:05:06.488184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:06.488184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hihJBbJYdNZsnDpuZ853TLsHHfhZXCBVLi+jcpM78y6aVOxDS65yDxSJFB8bZVkH1wBcNh5YZS9yrUGbKzWwDg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:06.488613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.14898","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42b3b6aa284d129549213d487df09c1267f2fe295d7638ca0b08cfa9d484d105","sha256:82f217816d13bcb8d11e6a160e4aa115a974be7037fb9ae35f39d281fcd9fcbf"],"state_sha256":"f934f0184abaf60dce5e3262b8407667f6dfc25b3ee5f5ddb8930d7e9b971daf"}