Poster
PAC Reinforcement Learning with Rich Observations
Akshay Krishnamurthy · Alekh Agarwal · John Langford

Mon Dec 5th 06:00 -- 09:30 PM @ Area 5+6+7+8 #58 #None
in Monday Posters »

We propose and study a new model for reinforcement learning with rich observations, generalizing contextual bandits to sequential decision making. These models require an agent to take actions based on observations (features) with the goal of achieving long-term performance competitive with a large set of policies. To avoid barriers to sample-efficient learning associated with large observation spaces and general POMDPs, we focus on problems that can be summarized by a small number of hidden states and have long-term rewards that are predictable by a reactive function class. In this setting, we design and analyze a new reinforcement learning algorithm, Least Squares Value Elimination by Exploration. We prove that the algorithm learns near optimal behavior after a number of episodes that is polynomial in all relevant parameters, logarithmic in the number of policies, and independent of the size of the observation space. Our result provides theoretical justification for reinforcement learning with function approximation.

Keywords: Bandit Algorithms · Learning Theory · Reinforcement Learning Algorithms

Author Information

Akshay Krishnamurthy (UMass Amherst)
Alekh Agarwal (Microsoft)
John Langford (Microsoft Research New York)

More from the Same Authors