35 citations · 112 across the 25 of their papers we have counts for
26 papers
Model approximation in MDPs with unbounded per-step cost
Berk Bozkurt, Aditya Mahajan, Ashutosh Nayyar +1
We consider the problem of designing a control policy for an infinite-horizon discounted cost Markov decision process when we only have access to an approximate model…
An Approach to Stochastic Dynamic Games with Asymmetric Information and Hidden Actions
Yi Ouyang, Hamidreza Tavafoghi, Demosthenis Teneketzis
We consider in discrete time, a general class of sequential stochastic dynamic games with asymmetric information with the following features. The underlying system has Markovian dy…
Scalable regret for learning to control network-coupled subsystems with unknown dynamics
Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar +1
We consider the problem of controlling an unknown linear quadratic Gaussian (LQG) system consisting of multiple subsystems connected over a network. Our goal is to minimize and qua…
A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan +2
We revisit the Thompson sampling algorithm to control an unknown linear quadratic (LQ) system recently proposed by Ouyang et al (arXiv:1709.04047). The regret bound of the algorith…
Training a Resilient Q-Network against Observational Interference
Chao-Han Huck Yang, I-Te Danny Hung, Yi Ouyang +1
Deep reinforcement learning (DRL) has demonstrated impressive performance in various gaming simulators and real-world applications. In practice, however, a DRL agent may receive fa…
Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
Daisuke Nishiyama, Mario Ynocente Castro, Shirou Maruyama +7
Automated Vehicles require exhaustive testing in simulation to detect as many safety-critical failures as possible before deployment on public roads. In this work, we focus on the…