Multi-Task Policy Search
This addresses the challenge of impracticality in training individual policies for every task, particularly for continuous variations, benefiting robotics and reinforcement learning, though it appears incremental as it builds on multi-task learning principles.
The paper tackles the problem of learning policies that generalize across multiple tasks in reinforcement learning and robotics, presenting a novel approach that learns a single nonlinear feedback policy parametrized by both state and task, with applications demonstrated in real-robot experiments.
Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for continuous task variations, requiring more principled approaches to share and transfer knowledge among similar tasks. We present a novel approach for learning a nonlinear feedback policy that generalizes across multiple tasks. The key idea is to define a parametrized policy as a function of both the state and the task, which allows learning a single policy that generalizes across multiple known and unknown tasks. Applications of our novel approach to reinforcement and imitation learning in real-robot experiments are shown.