On the Convergence of Modified Policy Iteration in Risk-Sensitive Exponential Cost Markov Decision Processes

• Yashaswini Murthy

  Corresponding Author

  Yashaswini Murthy

  [email protected]

  https://orcid.org/0000-0002-8788-6873

  Computing and Mathematical Sciences, California Institute of Technology, Pasadena, California 91125

  Search for more papers by this author

  ,
• Mehrdad Moharrami

  Mehrdad Moharrami

  [email protected]

  https://orcid.org/0000-0003-3907-8406

  Computer Science, University of Iowa, Iowa City, Iowa 52242

  Search for more papers by this author

  ,
• Rayadurgam Srikant

  Rayadurgam Srikant

  [email protected]

  https://orcid.org/0000-0003-1483-5204

  Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois Urbana-Champaign, Champaign, Illinois 61820

  Search for more papers by this author