{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U6ODENF2JWIIOFFYPRGABWYUCD","short_pith_number":"pith:U6ODENF2","schema_version":"1.0","canonical_sha256":"a79c3234ba4d908714b87c4c00db1410ffcbfdceb85eee83269a3a28a5286f0e","source":{"kind":"arxiv","id":"1807.10244","version":1},"attestation_state":"computed","paper":{"title":"Action-Constrained Markov Decision Processes With Kullback-Leibler Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ana Bu\\v{s}i\\'c, Sean Meyn","submitted_at":"2018-07-26T17:07:05Z","abstract_excerpt":"This paper concerns computation of optimal policies in which the one-step reward function contains a cost term that models Kullback-Leibler divergence with respect to nominal dynamics. This technique was introduced by Todorov in 2007, where it was shown under general conditions that the solution to the average-reward optimality equations reduce to a simple eigenvector problem. Since then many authors have sought to apply this technique to control problems and models of bounded rationality in economics.\n  A crucial assumption is that the input process is essentially unconstrained. For example, "},"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":"1807.10244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-26T17:07:05Z","cross_cats_sorted":[],"title_canon_sha256":"482812628abfe3b782dd95fc3f7ebab4cf0cce0fb774580c4adc0e7d57685c0f","abstract_canon_sha256":"e49303f477a24e146da7f1de6bb89ee0b97b0a3c39b757d33cda6d4e0ae068ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:42.759742Z","signature_b64":"ANB2+fll0H7CX6Lv/cog7K6Fb2K5lcPJsj4r/KDjXAw6otq3EAiIhA73T9CdSDdg/cjFQXl9LP5dYVTtGnBCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a79c3234ba4d908714b87c4c00db1410ffcbfdceb85eee83269a3a28a5286f0e","last_reissued_at":"2026-05-18T00:09:42.759158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:42.759158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action-Constrained Markov Decision Processes With Kullback-Leibler Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ana Bu\\v{s}i\\'c, Sean Meyn","submitted_at":"2018-07-26T17:07:05Z","abstract_excerpt":"This paper concerns computation of optimal policies in which the one-step reward function contains a cost term that models Kullback-Leibler divergence with respect to nominal dynamics. This technique was introduced by Todorov in 2007, where it was shown under general conditions that the solution to the average-reward optimality equations reduce to a simple eigenvector problem. Since then many authors have sought to apply this technique to control problems and models of bounded rationality in economics.\n  A crucial assumption is that the input process is essentially unconstrained. For example, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10244","kind":"arxiv","version":1},"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":"1807.10244","created_at":"2026-05-18T00:09:42.759260+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.10244v1","created_at":"2026-05-18T00:09:42.759260+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10244","created_at":"2026-05-18T00:09:42.759260+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6ODENF2JWII","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6ODENF2JWIIOFFY","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6ODENF2","created_at":"2026-05-18T12:32:56.356000+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/U6ODENF2JWIIOFFYPRGABWYUCD","json":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD.json","graph_json":"https://pith.science/api/pith-number/U6ODENF2JWIIOFFYPRGABWYUCD/graph.json","events_json":"https://pith.science/api/pith-number/U6ODENF2JWIIOFFYPRGABWYUCD/events.json","paper":"https://pith.science/paper/U6ODENF2"},"agent_actions":{"view_html":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD","download_json":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD.json","view_paper":"https://pith.science/paper/U6ODENF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.10244&json=true","fetch_graph":"https://pith.science/api/pith-number/U6ODENF2JWIIOFFYPRGABWYUCD/graph.json","fetch_events":"https://pith.science/api/pith-number/U6ODENF2JWIIOFFYPRGABWYUCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/action/storage_attestation","attest_author":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/action/author_attestation","sign_citation":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/action/citation_signature","submit_replication":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/action/replication_record"}},"created_at":"2026-05-18T00:09:42.759260+00:00","updated_at":"2026-05-18T00:09:42.759260+00:00"}