Bounded Optimal Exploration in MDP
This addresses the practical need for fast learning in reinforcement learning, though it appears incremental as it builds on existing PAC-MDP frameworks.
The paper tackles the problem of achieving satisfactory behavior quickly in reinforcement learning by relaxing PAC-MDP conditions, proposing simple algorithms for discrete and continuous state spaces with theoretical and numerical benefits.
Within the framework of probably approximately correct Markov decision processes (PAC-MDP), much theoretical work has focused on methods to attain near optimality after a relatively long period of learning and exploration. However, practical concerns require the attainment of satisfactory behavior within a short period of time. In this paper, we relax the PAC-MDP conditions to reconcile theoretically driven exploration methods and practical needs. We propose simple algorithms for discrete and continuous state spaces, and illustrate the benefits of our proposed relaxation via theoretical analyses and numerical examples. Our algorithms also maintain anytime error bounds and average loss bounds. Our approach accommodates both Bayesian and non-Bayesian methods.