Full Abstract:
We propose a framework for ensuring safe behavior of a reinforcement learning
agent when the reward function may be difficult to specify. In 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 consis-
tent 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 behav-
ior 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.
105
0
Learning Safe Policies with Expert Guidance
attributed to: Jessie 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 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...
0
Vulnerabilities & Strengths