Year: 2018
Type: conference-paper
Abstract: During training, model-free reinforcement learning (RL) systems can explore actions that lead to harmful or costly consequences. Having a human "in the loop'' and ready to intervene at all times can prevent these mistakes, but is prohibitively expensive for current algorithms. We explore how human oversight can be combined with a supervised learning system to prevent catastrophic events during training. We demonstrate this scheme on Atari games, with a Deep RL agent being overseen by a human for four hours. When the class of catastrophes is simple, we are able to prevent all catastrophes without affecting the agent's learning (whereas an RL baseline fails due to catastrophic forgetting).
DOI: 10.65109/mzmg4429
Authors: William Saunders, Girish Sastry, Andreas Stuhlmüller, Owain Evans
Institutions: University of Oxford, Stanford University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2964273112