no code implementations • NeurIPS 2012 • Jaedeug Choi, Kee-Eung Kim
We present a nonparametric Bayesian approach to inverse reinforcement learning (IRL) for multiple reward functions.
no code implementations • NeurIPS 2011 • Jaedeug Choi, Kee-Eung Kim
The difficulty in inverse reinforcement learning (IRL) arises in choosing the best reward function since there are typically an infinite number of reward functions that yield the given behaviour data as optimal.