Multi-Task Policy Search

TL;DR

This paper introduces a novel nonlinear feedback policy that generalizes across multiple tasks in reinforcement learning and robotics by incorporating task parameters into the policy, enabling effective transfer and sharing of knowledge.

Contribution

It proposes a new approach to learn a single policy conditioned on both state and task, facilitating generalization across known and unknown tasks.

Findings

Successful application in real-robot experiments

Effective transfer of knowledge across tasks

Policy generalizes to unseen tasks

Abstract

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.