My research is primarily focused on single- and multi-agent decision-theoretic planning and learning, especially reinforcement learning and stochastic optimization methods such as neuroevolution. Below is a list of my primary research areas and some current topics therein.  To find out more, check out my complete publication list.

Reinforcement Learning

1. • Robust empirical evaluation of reinforcement learning methods
   

2. • Automatic shaping for multi-task reinforcement learning
   

3. • State abstraction for multi-task reinforcement learning
   

4. • Feature selection and other state representation issues
   

5. • Applications to information retrieval
   

Multiagent Systems

1. • Multiagent reinforcement learning
   

2. • Multiagent neuroevolution
   

3. • Dec-POMDPs
   

Neuroevolution

1. • Applications to helicopter control
   

2. • Coevolutionary fitness modeling
   

3. • Efficient resampling