Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines

TL;DR

This paper introduces a lifelong reinforcement learning framework that uses temporal logic formulas and reward machines to enable efficient learning and transfer of high-level tasks over time.

Contribution

It proposes a novel combination of Sequential Linear Temporal Logic and Reward Machines for structured task representation and transfer in lifelong reinforcement learning.

Findings

LSRM outperforms scratch learning methods.

Task decomposition improves learning efficiency.

Knowledge transfer accelerates lifelong learning.

Abstract

Continuously learning new tasks using high-level ideas or knowledge is a key capability of humans. In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which enables an agent to leverage previously learned knowledge to fasten learning of logically specified tasks. For the sake of more flexible specification of tasks, we first introduce Sequential Linear Temporal Logic (SLTL), which is a supplement to the existing Linear Temporal Logic (LTL) formal language. We then utilize Reward Machines (RM) to exploit structural reward functions for tasks encoded with high-level events, and propose automatic extension of RM and efficient knowledge transfer over tasks for continuous learning in lifetime. Experimental results show that LSRM outperforms the methods that learn the target tasks from scratch by taking advantage of the task decomposition using SLTL and knowledge transfer over RM during the lifelong learning process.