{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QIRMDXTPKS6TPDF4PJT3NAZHOB","short_pith_number":"pith:QIRMDXTP","schema_version":"1.0","canonical_sha256":"8222c1de6f54bd378cbc7a67b68327707772a0fe14563ea8e7b8e29290d02a6e","source":{"kind":"arxiv","id":"2510.14898","version":2},"attestation_state":"computed","paper":{"title":"Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"David \\v{S}i\\v{s}ka, Denis Zorba, Lukasz Szpruch","submitted_at":"2025-10-16T17:16:28Z","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"},"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":"2510.14898","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-10-16T17:16:28Z","cross_cats_sorted":[],"title_canon_sha256":"14d38c748939a8e8e2c492139202ff9f65d51bf3620edf6fcce85c4865f218df","abstract_canon_sha256":"daa6b6a60977c4323060fcd187328b3cd8cad9852f985631f9ae2a2fe3cd361f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:06.488613Z","signature_b64":"hihJBbJYdNZsnDpuZ853TLsHHfhZXCBVLi+jcpM78y6aVOxDS65yDxSJFB8bZVkH1wBcNh5YZS9yrUGbKzWwDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8222c1de6f54bd378cbc7a67b68327707772a0fe14563ea8e7b8e29290d02a6e","last_reissued_at":"2026-06-03T01:05:06.488184Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:06.488184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of an actor-critic gradient flow for entropy regularised MDPs in general spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"David \\v{S}i\\v{s}ka, Denis Zorba, Lukasz Szpruch","submitted_at":"2025-10-16T17:16:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14898","kind":"arxiv","version":2},"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/2510.14898/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":"2510.14898","created_at":"2026-06-03T01:05:06.488244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.14898v2","created_at":"2026-06-03T01:05:06.488244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14898","created_at":"2026-06-03T01:05:06.488244+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIRMDXTPKS6T","created_at":"2026-06-03T01:05:06.488244+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIRMDXTPKS6TPDF4","created_at":"2026-06-03T01:05:06.488244+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIRMDXTP","created_at":"2026-06-03T01:05:06.488244+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/QIRMDXTPKS6TPDF4PJT3NAZHOB","json":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB.json","graph_json":"https://pith.science/api/pith-number/QIRMDXTPKS6TPDF4PJT3NAZHOB/graph.json","events_json":"https://pith.science/api/pith-number/QIRMDXTPKS6TPDF4PJT3NAZHOB/events.json","paper":"https://pith.science/paper/QIRMDXTP"},"agent_actions":{"view_html":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB","download_json":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB.json","view_paper":"https://pith.science/paper/QIRMDXTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.14898&json=true","fetch_graph":"https://pith.science/api/pith-number/QIRMDXTPKS6TPDF4PJT3NAZHOB/graph.json","fetch_events":"https://pith.science/api/pith-number/QIRMDXTPKS6TPDF4PJT3NAZHOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB/action/storage_attestation","attest_author":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB/action/author_attestation","sign_citation":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB/action/citation_signature","submit_replication":"https://pith.science/pith/QIRMDXTPKS6TPDF4PJT3NAZHOB/action/replication_record"}},"created_at":"2026-06-03T01:05:06.488244+00:00","updated_at":"2026-06-03T01:05:06.488244+00:00"}