Portrait de Jessie Huang n'est pas disponible

Jessie Huang

Alumni

Publications

Learning Safe Policies with Expert Guidance
Jessie Huang
Je-chun Huang
Fa Wu
Doina Precup
Yang Cai
We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In… (voir plus) order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the space of rewards consistent with its existing knowledge. We propose two methods to solve the resulting optimization: an exact ellipsoid-based method and a method in the spirit of the "follow-the-perturbed-leader" algorithm. Our experiments demonstrate the behavior of our algorithm in both discrete and continuous problems. The trained agent safely avoids states with potential negative effects while imitating the behavior of the expert in the other states.
2017-12-31
Advances in Neural Information Processing Systems 31 (NeurIPS 2018) (publié)
arxiv.org
arxiv.org