5 papers
Limiting-Kernel Q(): Bridging Short and Long Horizons
Tolga Ok, Arman Sharifi Kolarijani, Peyman Mohajerin Esfahani +1
In reinforcement learning, more accurate policy evaluation has been frequently shown to improve downstream policy optimization performance. For tractability, most value estimators…
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…
Offline Reinforcement Learning via Inverse Optimization
Ioannis Dimanidis, Tolga Ok, Peyman Mohajerin Esfahani
Inspired by the recent successes of Inverse Optimization (IO) across various application domains, we propose a novel offline Reinforcement Learning (ORL) algorithm for continuous s…
Scalable Kernel Inverse Optimization
Youyuan Long, Tolga Ok, Pedro Zattoni Scroccaro +1
Inverse Optimization (IO) is a framework for learning the unknown objective function of an expert decision-maker from a past dataset. In this paper, we extend the hypothesis class…