Description
Organizer and chair: Isaac Grosof
Stochastic approximation algorithms are quite popular in reinforcement learning notably because they are powerful tools to study the convergence of algorithms based on stochastic gradient descent (like Q-learning of policy gradient). In this talk, I will focus on constant step-size stochastic approximation and present tools to compute its asymptotic bias, which is non-zero (both for Martingale...
Infinite-state Markov Decision Processes (MDPs) are essential in modeling and optimizing a wide variety of engineering problems. In the reinforcement learning (RL) context, a variety of algorithms have been developed to learn and optimize these MDPs. At the heart of many popular policy-gradient based learning algorithms, such as natural actor-critic, TRPO, and PPO, lies the Natural Policy...
In the context of average reward Markov Decision Processes (MDPs), traditional approaches for obtaining performance bounds based on discounted reward formulations fail to provide meaningful bounds due to their dependence on the horizon. This limitation arises because average reward problems can be viewed as discounted reward problems, with the discount factor approaching 1, effectively...
