{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:W4O7EP7KDB67FDXXZOML2T54EX","short_pith_number":"pith:W4O7EP7K","schema_version":"1.0","canonical_sha256":"b71df23fea187df28ef7cb98bd4fbc25edefe830f1b4b183a1e495e326a56301","source":{"kind":"arxiv","id":"1112.1996","version":2},"attestation_state":"computed","paper":{"title":"KL-learning: Online solution of Kullback-Leibler control problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.OC","authors_text":"Bert Kappen, Joris Bierkens","submitted_at":"2011-12-09T01:35:06Z","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"},"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":"1112.1996","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-12-09T01:35:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd189e265881f7d6eaf07ddfbe9f0d78f3a405fd9db85289a173469ff1c6183e","abstract_canon_sha256":"52827674c25b091693dadf464cbe2b83f367fd3186e88d70a54857630266cedb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:13.314476Z","signature_b64":"y25LXdTeB41lomr1H7xwK4tB/ykkWS5MEzHsgUcHfCxa77AbFaz6y5237jg0m/DP8Vq0mWsSkiUECgQYoALMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b71df23fea187df28ef7cb98bd4fbc25edefe830f1b4b183a1e495e326a56301","last_reissued_at":"2026-05-18T04:02:13.313735Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:13.313735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KL-learning: Online solution of Kullback-Leibler control problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"math.OC","authors_text":"Bert Kappen, Joris Bierkens","submitted_at":"2011-12-09T01:35:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1112.1996","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":""},"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":"1112.1996","created_at":"2026-05-18T04:02:13.313854+00:00"},{"alias_kind":"arxiv_version","alias_value":"1112.1996v2","created_at":"2026-05-18T04:02:13.313854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1112.1996","created_at":"2026-05-18T04:02:13.313854+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4O7EP7KDB67","created_at":"2026-05-18T12:26:44.992195+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4O7EP7KDB67FDXX","created_at":"2026-05-18T12:26:44.992195+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4O7EP7K","created_at":"2026-05-18T12:26:44.992195+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/W4O7EP7KDB67FDXXZOML2T54EX","json":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX.json","graph_json":"https://pith.science/api/pith-number/W4O7EP7KDB67FDXXZOML2T54EX/graph.json","events_json":"https://pith.science/api/pith-number/W4O7EP7KDB67FDXXZOML2T54EX/events.json","paper":"https://pith.science/paper/W4O7EP7K"},"agent_actions":{"view_html":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX","download_json":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX.json","view_paper":"https://pith.science/paper/W4O7EP7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1112.1996&json=true","fetch_graph":"https://pith.science/api/pith-number/W4O7EP7KDB67FDXXZOML2T54EX/graph.json","fetch_events":"https://pith.science/api/pith-number/W4O7EP7KDB67FDXXZOML2T54EX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX/action/storage_attestation","attest_author":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX/action/author_attestation","sign_citation":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX/action/citation_signature","submit_replication":"https://pith.science/pith/W4O7EP7KDB67FDXXZOML2T54EX/action/replication_record"}},"created_at":"2026-05-18T04:02:13.313854+00:00","updated_at":"2026-05-18T04:02:13.313854+00:00"}