7 papers
Limiting-Kernel Q(): Bridging Short and Long Horizons
Tolga Ok, Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani +1
In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance. The widely adopted family o…
Benign Geometry and Distributional Robustness of Synthesis
Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani, Tamás Keviczky +1
In this paper, we study standard and distributionally robust synthesis problem of a stabilizing state-feedback controller for discrete-time linear time-invariant sy…
Control and Reinforcement Learning through the Lens of Optimization: An Algorithmic Perspective
Tolga Ok, Arman Sharifi Kolarijani, Mohamad Amin Sharif Kolarijani +1
The connection between control algorithms for Markov decision processes and optimization algorithms has been implicitly and explicitly exploited since the introduction of dynamic p…
Rank-One Modified Value Iteration
Arman Sharifi Kolarijani, Tolga Ok, Peyman Mohajerin Esfahani +1
In this paper, we provide a novel algorithm for solving planning and learning problems of Markov decision processes. The proposed algorithm follows a policy iteration-type update b…
Fast Approximate Dynamic Programming for Infinite-Horizon Markov Decision Processes
M. A. S. Kolarijani, G. F. Max, P. Mohajerin Esfahani
In this study, we consider the infinite-horizon, discounted cost, optimal control of stochastic nonlinear systems with separable cost and constraints in the state and input variabl…
Fast Approximate Dynamic Programming for Input-Affine Dynamics
M. A. S. Kolarijani, P. Mohajerin Esfahani
We propose two novel numerical schemes for approximate implementation of the dynamic programming~(DP) operation concerned with finite-horizon, optimal control of discrete-time syst…