Research Directions

The research I am currently interested in encompasses three main areas: Artificial Neural Networks, Reinforcement Learning, Evolutionary Algorithms and Simulation and modelling. This is a list of the papers I am currently working on. They will be available for public download once complete.

Genetic Programming for defining options in Temporally Abstract Learning. (in prep.)
Reinforcement learning with continuous action values Abstract
Multiple agents and the maximization of expected reward. (in prep.)
Maximizing total expected reward for multiple agents with conflicting goals. (in prep.)
Selfish neurons: Models of reinforcement for neural computing elements. (in prep.)