Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention

Author/Creator ORCID

Date

2019-03-22

Department

Program

Citation of Original Publication

Bharat Prakash, Mohit Khatwani, Nicholas Waytowich, Tinoosh Mohsenin, Improving Safety in Reinforcement Learning Using Model-Based Architectures and Human Intervention, 2019, https://arxiv.org/abs/1903.09328

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.

Abstract

Recent progress in AI and Reinforcement learning has shown great success in solving complex problems with high dimensional state spaces. However, most of these successes have been primarily in simulated environments where failure is of little or no consequence. Most real-world applications, however, require training solutions that are safe to operate as catastrophic failures are inadmissible especially when there is human interaction involved. Currently, Safe RL systems use human oversight during training and exploration in order to make sure the RL agent does not go into a catastrophic state. These methods require a large amount of human labor and it is very difficult to scale up. We present a hybrid method for reducing the human intervention time by combining model-based approaches and training a supervised learner to improve sample efficiency while also ensuring safety. We evaluate these methods on various grid-world environments using both standard and visual representations and show that our approach achieves better performance in terms of sample efficiency, number of catastrophic states reached as well as overall task performance compared to traditional model-free approaches.