We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous w...
The aim of transfer learning is to accelerate learning in related domains. In reinforcement learning, many different features such as a value function and a policy can be transfer...
The current evaluation functions for heuristic planning are expensive to compute. In numerous domains these functions give good guidance on the solution, so it worths the computat...
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
Several algorithms for learning near-optimal policies in Markov Decision Processes have been analyzed and proven efficient. Empirical results have suggested that Model-based Inter...