3 papers
cs.LG2026
Cross-fitted Proximal Learning for Model-Based Reinforcement Learning
Nishanth Venkatesh, Andreas A. Malikopoulos
Model-based reinforcement learning is attractive for sequential decision-making because it explicitly estimates reward and transition models and then supports planning through simu…
cs.LG2025
Model-Based Reinforcement Learning Under Confounding
Nishanth Venkatesh, Andreas A. Malikopoulos
We investigate model-based reinforcement learning in contextual Markov decision processes (C-MDPs) in which the context is unobserved and induces confounding in the offline dataset…
math.OC2023
Stochastic Control with Distributionally Robust Constraints for Cyber-Physical Systems Vulnerable to Attacks
Nishanth Venkatesh, Aditya Dave, Ioannis Faros +1
In this paper, we investigate the control of a cyber-physical system (CPS) while accounting for its vulnerability to external attacks. We formulate a constrained stochastic problem…