Accelerating Reinforcement Learning for Reaching using Continuous Curriculum Learning
This addresses the data efficiency problem in robot reinforcement learning for reaching tasks, though it appears incremental as it builds on existing curriculum learning concepts.
The paper tackles the problem of slow reinforcement learning training for robot multi-goal reaching tasks by proposing a precision-based continuous curriculum learning method that gradually adjusts requirements during training instead of using a fixed schedule. Experimental results with a Universal Robot 5e in simulation and real-world tests show this approach provides superior results faster than static schedules.
Reinforcement learning has shown great promise in the training of robot behavior due to the sequential decision making characteristics. However, the required enormous amount of interactive and informative training data provides the major stumbling block for progress. In this study, we focus on accelerating reinforcement learning (RL) training and improving the performance of multi-goal reaching tasks. Specifically, we propose a precision-based continuous curriculum learning (PCCL) method in which the requirements are gradually adjusted during the training process, instead of fixing the parameter in a static schedule. To this end, we explore various continuous curriculum strategies for controlling a training process. This approach is tested using a Universal Robot 5e in both simulation and real-world multi-goal reach experiments. Experimental results support the hypothesis that a static training schedule is suboptimal, and using an appropriate decay function for curriculum learning provides superior results in a faster way.