Multi-Task Reinforcement Learning with Context-based Representations

TL;DR

This paper introduces a multi-task reinforcement learning approach that leverages context-based, composable representations informed by metadata to improve task transfer and achieves state-of-the-art results in robotic manipulation benchmarks.

Contribution

It proposes a novel framework using context-dependent representations to enhance multi-task learning by effectively incorporating metadata for better knowledge transfer.

Findings

Achieved state-of-the-art results on Meta-World benchmark

Demonstrated improved task transfer using context-based representations

Showed the effectiveness of metadata in informing representation composition

Abstract

The benefit of multi-task learning over single-task learning relies on the ability to use relations across tasks to improve performance on any single task. While sharing representations is an important mechanism to share information across tasks, its success depends on how well the structure underlying the tasks is captured. In some real-world situations, we have access to metadata, or additional information about a task, that may not provide any new insight in the context of a single task setup alone but inform relations across multiple tasks. While this metadata can be useful for improving multi-task learning performance, effectively incorporating it can be an additional challenge. We posit that an efficient approach to knowledge transfer is through the use of multiple context-dependent, composable representations shared across a family of tasks. In this framework, metadata can help to learn interpretable representations and provide the context to inform which representations to compose and how to compose them. We use the proposed approach to obtain state-of-the-art results in Meta-World, a challenging multi-task benchmark consisting of 50 distinct robotic manipulation tasks.