*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Policy-based Exploration for Efficient Reinforcement Learning
Kaushik Subramanian
Ph.D. Candidate
School of Interactive Computing
College of Computing
Georgia Institute of Technology
Date: Wednesday, May 17th 2017
Time: 10 AM to 12 NOON ET
Location: CCB 345
Committee
--------------
Dr. Charles Isbell (Advisor, School of Interactive Computing, Georgia Institute of Technology)
Dr. Andrea Thomaz (Co-Advisor, Department of Electrical and Computer Engineering, University of Texas at Austin)
Dr. Mark Riedl (School of Interactive Computing, Georgia Institute of Technology)
Dr. Thad Starner (School of Interactive Computing, Georgia Institute of Technology)
Dr. Peter Stone (Department of Computer Science, University of Texas at Austin)
Abstract
--------------
Reinforcement Learning (RL) is the field of research focused on solving sequential decision-making tasks modeled as Markov Decision Processes. Researchers have shown RL to be successful at solving a variety of problems like system operations (logistics), robot tasks (soccer, helicopter control) and computer games (backgammon); however, in general, it is well-known that standard RL approaches do not scale well with the size of the problem. The reason this problem arises is that RL approaches rely on obtaining samples useful for learning the underlying structure. In this work we tackle the problem of smart exploration in RL, by using human interaction. We propose policy-based methods that serve to effectively bias exploration towards important aspects of the domain.
Reinforcement Learning agents use function approximation methods to generalize over large and complex domains. One of the most well-studied approaches is using linear regression algorithms to model the value function of the decision-making problem. We introduce a policy-based method that uses statistical criteria derived from linear regression analysis to bias the agent to explore samples useful for learning. We show how we can learn exploration policies autonomously and from human demonstrations (using concepts of active learning) to facilitate fast convergence to the optimal policy. We then tackle the problem of human-guided exploration in RL. We present a probabilistic method which combines human evaluations, instantiated as policy signals, with Bayesian RL. We show how this approach provides performance speedups while being robust to noisy, suboptimal human signals. We also present an approach that makes use of some of the inherent structure in the exploratory human demonstrations to assist Monte Carlo RL to overcome its limitations and efficiently solve large-scale problems. We implement our methods on popular arcade games and highlight the improvements achieved using our approach. We show how the work on using humans to help agents efficiently explore sequential decision-making tasks is an important and necessary step in applying Reinforcement Learning to complex problems
