References of "Regan, Kevin"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailAn analytic solution to discrete Bayesian reinforcement learning
Poupart, Pascal; Vlassis, Nikos UL; Hoey, Jesse et al

in Proc Int. Conf. on Machine Learning, Pittsburgh, USA (2006)

Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms come short of achieving ... [more ▼]

Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms come short of achieving this goal because the amount of exploration required is often too costly and/or too time consuming for online learning. As a result, RL is mostly used for offline learning in simulated environments. We propose a new algorithm, called BEETLE, for effective online learning that is computationally efficient while minimizing the amount of exploration. We take a Bayesian model-based approach, framing RL as a partially observable Markov decision process. Our two main contributions are the analytical derivation that the optimal value function is the upper envelope of a set of multivariate polynomials, and an efficient point-based value iteration algorithm that exploits this simple parameterization. [less ▲]

Detailed reference viewed: 45 (0 UL)