Hybrid computer approach to train a machine learning system
This addresses the problem of environment simulation for reinforcement learning researchers, but appears incremental as it applies an existing hybrid approach to a specific task.
The authors tackled the challenge of simulating environments for reinforcement learning by using a hybrid computer setup combining digital and analog computers, and demonstrated it by training a system to balance an inverted pendulum.
This book chapter describes a novel approach to training machine learning systems by means of a hybrid computer setup i.e. a digital computer tightly coupled with an analog computer. As an example a reinforcement learning system is trained to balance an inverted pendulum which is simulated on an analog computer, thus demonstrating a solution to the major challenge of adequately simulating the environment for reinforcement learning.