List of Publications and Preprints

Journals

• A Policy Gradient Algorithm for the Risk-Sensitive Exponential Cost MDP.
  Mehrdad Moharrami, Yashaswini Murthy, Arghyadip Roy, R. Srikant.
  Math of Operations Research, 2024. (Paper)

• On the Convergence of Modified Policy Iteration in Risk Sensitive Exponential Cost Markov Decision Processes,
  Yashaswini Murthy, Mehrdad Moharrami, R. Srikant.
  Major Revision at Operations Research, 2024. (Paper)

• Performance of NPG in Countable State-Space Average-Cost RL.
  Yashaswini Murthy, Isaac Grosof, Siva Theja Maguluri, R. Srikant. (Paper)
  Major Revision at Operations Research, 2024.

• smartSDH: A Mechanism Design Approach to Building Control.
  Ioannis C. Konstantakopoulos, Kristy A. Hamilton, Yashaswini Murthy, Tanya Veeravalli, Costas Spanos and Roy Dong.
  IEEE Systems Journal, 2022. (Paper)

Conferences

• Finite-Time Bounds for Distributionally Robust TD Learning with Linear Function Approximation.
  Saptarshi Mandal, Yashaswini Murthy and R. Srikant.
  Under Review at ICLR 2026.

• On the Gaussian Limit of the Output of IIR Filters.
  Yashaswini Murthy, Bassam Bamieh and R. Srikant.
  IEEE Conference on Decision and Control (CDC), 2025. (Paper)

• Global Convergence of Policy Gradient in Average Reward Markov Decision Processes.
  Yashaswini Murthy*, Navdeep Kumar*, Itai Shufaro, Kfir Levy, R. Srikant and Shie Mannor. (*: Equal Contribution)
  International Conference on Learning Representations (ICLR) 2025. (Paper)

• Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms.
  Yashaswini Murthy, Mehrdad Moharrami, R. Srikant.
  Advances in Neural Information Processing Systems (NeurIPS), 2023. (Paper)

• Modified Policy Iteration for Exponential Cost Risk Sensitive MDPs.
  Yashaswini Murthy, Mehrdad Moharrami, R. Srikant.
  Learning for Dynamics and Control (L4DC) 2023. (Paper)

• On the Convergence of Natural Policy Gradient and Mirror Descent-Like Policy Methods for Average-Reward MDPs.
  Yashaswini Murthy and R. Srikant.
  IEEE Conference on Decision and Control (CDC), 2023. (Paper)

• A Lagrangian Model to Predict Microscallop Motion in non Newtonian Fluids,
  Yashaswini Murthy and Ravi Banavar.
  International Conference on Manipulation Automation and Robotics at Small Scales (MARSS), 2019, IEEE.
  Invited for journal extension. (Paper)

• The Twelvefold Way of Non-Sequential Lossless Compression.
  T. Ameen ur Rahman*, A. Barbehenn*, X. Chen*, H. Dbouk*, J. Douglas*, Y. Geng*, I. George*, J. Harvill*, S. Jeon*, K. Kansal*, K. Lee*, K. Levick*, B. Li*, Z. Li*,
  Y. Murthy*, A. Muthuveeru-Subramaniam*, S. Olmez*, M. Tomei*, T. Veeravalli*, X. Wang*, E. Wayman*, F. Wu*, P. Xu*,
  S. Yan*, H. Zhang*, Y. Zhang*, Y. Zhang*, Y. Zhao*, Sourya Basu, and Lav R. Varshney.
  Data Compression Conference, 2021, IEEE. (*: alphabetical ordering) (Paper)

Papers Under Submission/Preparation

• On the Performance of Actor-Critic Reinforcement Learning Algorithsm for Risk Sensitive Exponential Cost Markov Decision Processes.
  Yashaswini Murthy and R. Srikant. In preparation.

• A Theoretical Model of Microscallop in Non-Newtonian Fluids.
  Yashaswini Murthy. (Paper).

Theses

• Ph.D. Thesis: Policy-Based Average-Reward and Robust Markov Decision Processes and Reinforcement Learning. (Thesis)

• Masters Thesis: Microscallop Modelling, Motion Planning and Control. (Thesis).