Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning
This addresses the challenge of sample-efficient learning for robotics in physical tasks, though it is incremental as it applies known techniques to a specific domain.
The paper tackled the problem of rapid learning in physical environments by developing a robotic system that solves a real-world labyrinth game using model-based reinforcement learning, achieving success in only 5 hours of training data.
Motivated by the challenge of achieving rapid learning in physical environments, this paper presents the development and training of a robotic system designed to navigate and solve a labyrinth game using model-based reinforcement learning techniques. The method involves extracting low-dimensional observations from camera images, along with a cropped and rectified image patch centered on the current position within the labyrinth, providing valuable information about the labyrinth layout. The learning of a control policy is performed purely on the physical system using model-based reinforcement learning, where the progress along the labyrinth's path serves as a reward signal. Additionally, we exploit the system's inherent symmetries to augment the training data. Consequently, our approach learns to successfully solve a popular real-world labyrinth game in record time, with only 5 hours of real-world training data.