Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning

TL;DR

This paper introduces a novel method for skill generation in sparse-reward reinforcement learning by discretizing action spaces and using NLP-inspired tokenization, leading to more efficient exploration and better performance.

Contribution

It proposes a new approach combining action space clustering and tokenization to generate skills, reducing pretraining time and improving exploration in continuous action spaces.

Findings

Outperforms baseline skill-generation methods in challenging domains

Requires significantly less computation for skill creation and online rollouts

Effective in sparse-reward reinforcement learning tasks

Abstract

Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward. Moreover, in continuous action spaces there are an infinite number of possible actions, which only increases the difficulty of exploration. One class of methods designed to address these issues forms temporally extended actions, often called skills, from interaction data collected in the same domain, and optimizes a policy on top of this new action space. Typically such methods require a lengthy pretraining phase, especially in continuous action spaces, in order to form the skills before reinforcement learning can begin. Given prior evidence that the full range of the continuous action space is not required in such tasks, we propose a novel approach to skill-generation with two components. First we discretize the action space through clustering, and second we leverage a tokenization technique borrowed from natural language processing to generate temporally extended actions. Such a method outperforms baselines for skill-generation in several challenging sparse-reward domains, and requires orders-of-magnitude less computation in skill-generation and online rollouts. Our code is available at \url{https://github.com/dyunis/subwords_as_skills}.