{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/72985"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/72985","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Rational inattention in control of Markov chains","abstract":"This thesis poses a general model for optimal control subject to information constraint, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting in nite-dimensional convex program admits a decomposition based on the Bellman error, which is the subject of study in approximate dynamic programming. Later, we apply the general theory to an information-constrained variant of the scalar Linear-Quadratic-Gaussian (LQG) control problem. We give an upper bound on the optimal steady-state value of the quadratic performance objective and present explicit constructions of controllers that achieve this bound. We show that the obvious certainty-equivalent control policy is suboptimal when the information constraints are very severe, and propose another policy that performs better in this low-information regime. In the two extreme cases of no information (open-loop) and perfect information, these two policies coincide with the optimum.","abstract_html":"This thesis poses a general model for optimal control subject to information constraint, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting in nite-dimensional convex program admits a decomposition based on the Bellman error, which is the subject of study in approximate dynamic programming. Later, we apply the general theory to an information-constrained variant of the scalar Linear-Quadratic-Gaussian (LQG) control problem. We give an upper bound on the optimal steady-state value of the quadratic performance objective and present explicit constructions of controllers that achieve this bound. We show that the obvious certainty-equivalent control policy is suboptimal when the information constraints are very severe, and propose another policy that performs better in this low-information regime. In the two extreme cases of no information (open-loop) and perfect information, these two policies coincide with the optimum.","abstract_has_math":false,"creators":["Shafieepoorfard, Ehsan"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Raginsky, Maxim"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-01-21T19:55:22Z","date_published":"2015-01-21T19:55:22Z","updated_at":"2026-07-22T22:26:07Z","subjects":["Markov Chain","Information Theory","Control","Limited capacity","Optimization"],"languages":["en"],"rights":["Copyright 2014 Ehsan Shafieepoorfard"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/72985","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Raginsky, Maxim"]},{"key":"dc:creator","label":"Author","values":["Shafieepoorfard, Ehsan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-01-21T19:55:22Z","2017-01-22T10:15:25Z","2014-12","2015-01-21"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Markov Chain","Information Theory","Control","Limited capacity","Optimization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2014 Ehsan Shafieepoorfard"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/72985"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["This thesis poses a general model for optimal control subject to information constraint, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting in nite-dimensional convex program admits a decomposition based on the Bellman error, which is the subject of study in approximate dynamic programming. Later, we apply the general theory to an information-constrained variant of the scalar Linear-Quadratic-Gaussian (LQG) control problem. We give an upper bound on the optimal steady-state value of the quadratic performance objective and present explicit constructions of controllers that achieve this bound. We show that the obvious certainty-equivalent control policy is suboptimal when the information constraints are very severe, and propose another policy that performs better in this low-information regime. In the two extreme cases of no information (open-loop) and perfect information, these two policies coincide with the optimum.","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-08-04T14:14:05Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 Shafieepoorfard_Ehsan.tex: 6259 bytes, checksum: d627d06e872810c2831117945ae574f1 (MD5) Shafieepoorfard_Ehsan.pdf: 453798 bytes, checksum: dedd3848ce01ddaa50b24066a24e4b50 (MD5)","Made available in DSpace on 2015-01-21T19:55:22Z (GMT). No. of bitstreams: 2 Ehsan_Shafieepoorfard.pdf: 453798 bytes, checksum: dedd3848ce01ddaa50b24066a24e4b50 (MD5) Shafieepoorfard_Ehsan.tex: 6259 bytes, checksum: d627d06e872810c2831117945ae574f1 (MD5)","Embargo set by: Seth Robbins for item 73174 Lift date: 2017-01-21T19:56:18Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 73174 on 2017-01-22T10:15:25Z."]},{"key":"dc:title","label":"Title","values":["Rational inattention in control of Markov chains"]}]}],"canonical_facts":{"dc:contributor":["Raginsky, Maxim"],"dc:creator":["Shafieepoorfard, Ehsan"],"dc:date":["2015-01-21T19:55:22Z","2017-01-22T10:15:25Z","2014-12","2015-01-21"],"dc:description":["This thesis poses a general model for optimal control subject to information constraint, motivated in part by recent work on information-constrained decision-making by economic agents. In the average-cost optimal control framework, the general model introduced in this paper reduces to a variant of the linear-programming representation of the average-cost optimal control problem, subject to an additional mutual information constraint on the randomized stationary policy. The resulting in nite-dimensional convex program admits a decomposition based on the Bellman error, which is the subject of study in approximate dynamic programming. Later, we apply the general theory to an information-constrained variant of the scalar Linear-Quadratic-Gaussian (LQG) control problem. We give an upper bound on the optimal steady-state value of the quadratic performance objective and present explicit constructions of controllers that achieve this bound. We show that the obvious certainty-equivalent control policy is suboptimal when the information constraints are very severe, and propose another policy that performs better in this low-information regime. In the two extreme cases of no information (open-loop) and perfect information, these two policies coincide with the optimum.","Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-08-04T14:14:05Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 2 Shafieepoorfard_Ehsan.tex: 6259 bytes, checksum: d627d06e872810c2831117945ae574f1 (MD5) Shafieepoorfard_Ehsan.pdf: 453798 bytes, checksum: dedd3848ce01ddaa50b24066a24e4b50 (MD5)","Made available in DSpace on 2015-01-21T19:55:22Z (GMT). No. of bitstreams: 2 Ehsan_Shafieepoorfard.pdf: 453798 bytes, checksum: dedd3848ce01ddaa50b24066a24e4b50 (MD5) Shafieepoorfard_Ehsan.tex: 6259 bytes, checksum: d627d06e872810c2831117945ae574f1 (MD5)","Embargo set by: Seth Robbins for item 73174 Lift date: 2017-01-21T19:56:18Z Reason: Author requested U of Illinois access only (OA after 2yrs) in Vireo ETD system","U of I Only Restriction Lifted for Item 73174 on 2017-01-22T10:15:25Z."],"dc:identifier":["http://hdl.handle.net/2142/72985"],"dc:language":["en"],"dc:rights":["Copyright 2014 Ehsan Shafieepoorfard"],"dc:subject":["Markov Chain","Information Theory","Control","Limited capacity","Optimization"],"dc:title":["Rational inattention in control of Markov chains"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:07Z"}