Mobile phones offer a variety of interesting and exciting applications. A mobile phone can be a communication device, an entertainment device, and a learning device. J2ME is a pop...
— This paper shows that the distributed representation found in Learning Vector Quantization (LVQ) enables reinforcement learning methods to cope with a large decision search spa...
In this study, a learning device based on the PATtree data structures was developed. The original PAT-trees were enhanced with the deletion function to emulate human learning comp...
This paper analyzes the complexity of on-line reinforcement learning algorithms, namely asynchronous realtime versions of Q-learning and value-iteration, applied to the problem of...
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...