Timezone: »

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Chris Dann · Yishay Mansour · Mehryar Mohri · Ayush Sekhari · Karthik Sridharan

Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #1111

Myopic exploration policies such as epsilon-greedy, softmax, or Gaussian noise fail to explore efficiently in some reinforcement learning tasks and yet, they perform well in many others. In fact, in practice, they are often selected as the top choices, due to their simplicity. But, for what tasks do such policies succeed? Can we give theoretical guarantees for their favorable performance? These crucial questions have been scarcely investigated, despite the prominent practical importance of these policies. This paper presents a theoretical analysis of such policies and provides the first regret and sample-complexity bounds for reinforcement learning with myopic exploration. Our results apply to value-function-based algorithms in episodic MDPs with bounded Bellman Eluder dimension. We propose a new complexity measure called myopic exploration gap, denoted by \alpha, that captures a structural property of the MDP, the exploration policy and the given value function class. We show that the sample-complexity of myopic exploration scales quadratically with the inverse of this quantity, 1 / \alpha^2. We further demonstrate through concrete examples that myopic exploration gap is indeed favorable in several tasks where myopic exploration succeeds, due to the corresponding dynamics and reward structure.

Author Information

Chris Dann (Google)
Yishay Mansour (Google)
Mehryar Mohri (Google Research and Courant Institute of Mathematical Sciences)
Ayush Sekhari (Cornell University)
Karthik Sridharan (Cornell University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors