Toward Robust Long Range Policy Transfer

TL;DR

This paper introduces a hierarchical policy transfer method that enhances the diversity and adaptability of primitive policies, enabling more effective transfer to complex new tasks with continuous actions.

Contribution

It proposes a novel approach that trains a combination function and adapts primitive policies, with regularization to improve diversity, outperforming existing transfer methods.

Findings

Outperforms recent policy transfer methods in continuous action tasks.

Provides broader transferability range compared to prior approaches.

Regularization terms are crucial for effective long-range transfer.

Abstract

Humans can master a new task within a few trials by drawing upon skills acquired through prior experience. To mimic this capability, hierarchical models combining primitive policies learned from prior tasks have been proposed. However, these methods fall short comparing to the human's range of transferability. We propose a method, which leverages the hierarchical structure to train the combination function and adapt the set of diverse primitive polices alternatively, to efficiently produce a range of complex behaviors on challenging new tasks. We also design two regularization terms to improve the diversity and utilization rate of the primitives in the pre-training phase. We demonstrate that our method outperforms other recent policy transfer methods by combining and adapting these reusable primitives in tasks with continuous action space. The experiment results further show that our approach provides a broader transferring range. The ablation study also shows the regularization terms are critical for long range policy transfer. Finally, we show that our method consistently outperforms other methods when the quality of the primitives varies.