For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
Reinforcement learning policies face the exploration versus exploitation dilemma, i.e. the search for a balance between exploring the environment to find profitable actions while t...
Factored representations, model-based learning, and hierarchies are well-studied techniques for improving the learning efficiency of reinforcement-learning algorithms in large-sca...
Carlos Diuk, Alexander L. Strehl, Michael L. Littm...
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
Research in reinforcement learning has produced algorithms for optimal decision making under uncertainty that fall within two main types. The first employs a Bayesian framework, ...