Towards More Sample Efficiency in Reinforcement Learning with Data Augmentation
This addresses sample inefficiency in reinforcement learning for robotics, but appears incremental as it builds on existing data augmentation approaches.
The paper tackles the problem of high sample requirements in deep reinforcement learning for robotics by proposing two novel data augmentation techniques: Kaleidoscope Experience Replay and Goal-augmented Experience Replay, which preliminary results show lead to a large increase in learning speed.
Deep reinforcement learning (DRL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. We propose two novel data augmentation techniques for DRL in order to reuse more efficiently observed data. The first one called Kaleidoscope Experience Replay exploits reflectional symmetries, while the second called Goal-augmented Experience Replay takes advantage of lax goal definitions. Our preliminary experimental results show a large increase in learning speed.