Faster and Safer Training by Embedding High-Level Knowledge into Deep Reinforcement Learning

Understand

Deep reinforcement learning has been successfully used in many dynamic decision making domains, especially those with very large state spaces.

• However, it is also well-known that deep reinforcement learning can be very slow and resource intensive.
• The resulting system is often brittle and difficult to explain.
• In this paper, we attempt to address some of these problems by proposing a framework of Rule-interposing Learning (RIL) that embeds high level rules into the deep reinforcement learning.