My research interests include learning off-policy, reward shaping, ensembles in reinforcement learning, as well as some statistical learning methods and their use in efficient reinforcement learning.
I am currently working on the design of the high-level intelligent control for an assistive exoskeleton, in the context of the IWT-SBO project MIRAD.
Expressing Arbitrary Reward Functions as Potential-Based Advice. In Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15).. (2015).
Off-Policy Shaping Ensembles in Reinforcement Learning. In European Conference on Artificial Intelligence (ECAI). IOS Press.. (2014).