{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:W4O7EP7KDB67FDXXZOML2T54EX","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":"52827674c25b091693dadf464cbe2b83f367fd3186e88d70a54857630266cedb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-12-09T01:35:06Z","title_canon_sha256":"cd189e265881f7d6eaf07ddfbe9f0d78f3a405fd9db85289a173469ff1c6183e"},"schema_version":"1.0","source":{"id":"1112.1996","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1112.1996","created_at":"2026-05-18T04:02:13Z"},{"alias_kind":"arxiv_version","alias_value":"1112.1996v2","created_at":"2026-05-18T04:02:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1112.1996","created_at":"2026-05-18T04:02:13Z"},{"alias_kind":"pith_short_12","alias_value":"W4O7EP7KDB67","created_at":"2026-05-18T12:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"W4O7EP7KDB67FDXX","created_at":"2026-05-18T12:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"W4O7EP7K","created_at":"2026-05-18T12:26:44Z"}],"graph_snapshots":[{"event_id":"sha256:e6afd28c780b2755b7229a38f7569df0e1e2d112c736a023c44f086964c16e60","target":"graph","created_at":"2026-05-18T04:02:13Z","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"},"paper":{"abstract_excerpt":"We introduce a stochastic approximation method for the solution of an ergodic Kullback-Leibler control problem. A Kullback-Leibler control problem is a Markov decision process on a finite state space in which the control cost is proportional to a Kullback-Leibler divergence of the controlled transition probabilities with respect to the uncontrolled transition probabilities. The algorithm discussed in this work allows for a sound theoretical analysis using the ODE method. In a numerical experiment the algorithm is shown to be comparable to the power method and the related Z-learning algorithm i","authors_text":"Bert Kappen, Joris Bierkens","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-12-09T01:35:06Z","title":"KL-learning: Online solution of Kullback-Leibler control problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1112.1996","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":"sha256:879da937a8b0c38d294834ba18b736d54fac264c66c889be5da9286ffbf31e34","target":"record","created_at":"2026-05-18T04:02:13Z","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":"52827674c25b091693dadf464cbe2b83f367fd3186e88d70a54857630266cedb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-12-09T01:35:06Z","title_canon_sha256":"cd189e265881f7d6eaf07ddfbe9f0d78f3a405fd9db85289a173469ff1c6183e"},"schema_version":"1.0","source":{"id":"1112.1996","kind":"arxiv","version":2}},"canonical_sha256":"b71df23fea187df28ef7cb98bd4fbc25edefe830f1b4b183a1e495e326a56301","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b71df23fea187df28ef7cb98bd4fbc25edefe830f1b4b183a1e495e326a56301","first_computed_at":"2026-05-18T04:02:13.313735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:02:13.313735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y25LXdTeB41lomr1H7xwK4tB/ykkWS5MEzHsgUcHfCxa77AbFaz6y5237jg0m/DP8Vq0mWsSkiUECgQYoALMDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:02:13.314476Z","signed_message":"canonical_sha256_bytes"},"source_id":"1112.1996","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:879da937a8b0c38d294834ba18b736d54fac264c66c889be5da9286ffbf31e34","sha256:e6afd28c780b2755b7229a38f7569df0e1e2d112c736a023c44f086964c16e60"],"state_sha256":"b4f99b6805fee8ad953885e3d363782e57a389a5dad83ef1d636ab9f79c29ce8"}