Exploiting Transformer in Sparse Reward Reinforcement Learning for Interpretable Temporal Logic Motion Planning

TL;DR

This paper introduces T2TL, a novel framework that integrates Transformer models into reinforcement learning for interpretable temporal logic motion planning, improving task understanding and learning efficiency in complex robotic tasks.

Contribution

The paper proposes a Double-Transformer-guided Temporal Logic framework (T2TL) that enhances reinforcement learning with structured LTL instruction encoding and environment-agnostic pre-training.

Findings

T2TL effectively encodes LTL instructions for better task understanding.

Decomposition of tasks into sub-goals improves learning efficiency.

Simulation results validate the effectiveness of the proposed framework.

Abstract

Automaton based approaches have enabled robots to perform various complex tasks. However, most existing automaton based algorithms highly rely on the manually customized representation of states for the considered task, limiting its applicability in deep reinforcement learning algorithms. To address this issue, by incorporating Transformer into reinforcement learning, we develop a Double-Transformer-guided Temporal Logic framework (T2TL) that exploits the structural feature of Transformer twice, i.e., first encoding the LTL instruction via the Transformer module for efficient understanding of task instructions during the training and then encoding the context variable via the Transformer again for improved task performance. Particularly, the LTL instruction is specified by co-safe LTL. As a semantics-preserving rewriting operation, LTL progression is exploited to decompose the complex task into learnable sub-goals, which not only converts non-Markovian reward decision processes to Markovian ones, but also improves the sampling efficiency by simultaneous learning of multiple sub-tasks. An environment-agnostic LTL pre-training scheme is further incorporated to facilitate the learning of the Transformer module resulting in an improved representation of LTL. The simulation results demonstrate the effectiveness of the T2TL framework.