用于离线安全强化学习的时序逻辑规范条件化Decision Transformer
Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning
AI总结：
针对离线安全强化学习在复杂时序逻辑任务中的不足，提出时序逻辑规范条件化Decision Transformer（SDT）框架，结合STL表达力与DT序列建模能力，在DSRL基准上实现了更安全、高奖励的策略学习。
摘要：
离线安全强化学习（RL）旨在从固定数据集中训练出满足约束的策略。当前最先进的方法基于监督学习和条件化策略。然而，在涉及具有丰富时序和逻辑结构的复杂任务的实际应用中，这些方法存在不足。本文提出了时序逻辑规范条件化Decision Transformer（SDT），这是一种新颖的框架，利用信号时序逻辑（STL）的表达能力来指定智能体应遵循的复杂时序规则，并结合Decision Transformer（DT）的序列建模能力。在DSRL基准上的实证评估表明，与现有方法相比，SDT在学习安全和髙奖励策略方面具有更好的能力。此外，SDT在其所条件化的STL规范的不同期望满足程度方面表现出良好的一致性。
英文摘要：
Offline safe reinforcement learning (RL) aims to train a constraint satisfaction policy from a fixed dataset. Current state-of-the-art approaches are based on supervised learning with a conditioned policy. However, these approaches fall short in real-world applications that involve complex tasks with rich temporal and logical structures. In this paper, we propose temporal logic Specification-conditioned Decision Transformer (SDT), a novel framework that harnesses the expressive power of signal temporal logic (STL) to specify complex temporal rules that an agent should follow and the sequential modeling capability of Decision Transformer (DT). Empirical evaluations on the DSRL benchmarks demonstrate the better capacity of SDT in learning safe and high-reward policies compared with existing approaches. In addition, SDT shows good alignment with respect to different desired degrees of satisfaction of the STL specification that it is conditioned on.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
