Multi-task Learning for Continuous Control
This work addresses the challenge of multi-task learning for robotic agents in continuous control settings, but it is incremental as it extends existing methods to a new domain without introducing major innovations.
The paper tackled the problem of applying multi-task learning to continuous control tasks, which are more relevant for real-world robotics than discrete action spaces, and demonstrated that multi-task learning outperformed baselines and alternative knowledge sharing methods in simulated environments.
Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks. However, in the reinforcement learning domain, multi-task learning has not exhibited the same level of success as in other domains, such as computer vision. In addition, most reinforcement learning research on multi-task learning has been focused on discrete action spaces, which are not used for robotic control in the real-world. In this work, we apply multi-task learning methods to continuous action spaces and benchmark their performance on a series of simulated continuous control tasks. Most notably, we show that multi-task learning outperforms our baselines and alternative knowledge sharing methods.