We introduce the ALeRT (Action-dependent Learning Rates with Trends) algorithm that makes two modifications to the learning rate and one change to the exploration rate of traditio...
Maria Cutumisu, Duane Szafron, Michael H. Bowling,...
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
Abstract. We present first experiments using Support Vector Regression as function approximator for an on-line, sarsa-like reinforcement learner. To overcome the batch nature of S...
- This paper proposes the use of an interactive web based problem solving application that utilises flowchart based programming and code generation to address the issues faced by n...
Abstract. Learning to act in an unknown partially observable domain is a difficult variant of the reinforcement learning paradigm. Research in the area has focused on model-free m...