arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.06107cs.AI
收藏

EXPIL:面向游戏学习的解释性谓词发明

EXPIL: Explanatory Predicate Invention for Learning in Games

Technical University of Darmstadt(达姆施塔特工业大学);Hessian Center for Artificial Intelligence(黑森人工智能中心);German Research Centre for Artificial Intelligence(德国人工智能研究中心);Eindhoven University of Technology(埃因霍温理工大学)

Jingyuan Sha, Hikaru Shindo, Quentin Delfosse, Kristian Kersting, Devendra Singh Dhami

AI总结:

本文提出EXPIL方法,从预训练神经智能体中自动提取谓词用于逻辑智能体,以减少对预定义背景知识的依赖,并在多种游戏中验证其能以更少背景知识实现可解释行为。

摘要:

强化学习(RL)已被证明是训练在各种游戏中表现优异的智能体的强大工具。然而,神经网络模型的黑箱特性往往阻碍我们理解智能体动作背后的推理过程。近期研究尝试通过利用预训练神经智能体的指导来编码基于逻辑的策略,从而实现可解释的决策,以解决这一问题。这类方法的一个缺点是需要在谓词形式中提供大量预定义的背景知识,限制了其适用性和可扩展性。在本工作中,我们提出了一种新颖的方法,即面向游戏学习的解释性谓词发明(EXPIL),该方法从预训练的神经智能体中识别并提取谓词,随后用于基于逻辑的智能体,从而减少对预定义背景知识的依赖。我们在多种游戏上的实验评估表明,EXPIL 在需要较少背景知识的情况下,能够有效地使逻辑智能体实现可解释的行为。

英文摘要:

Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders our ability to understand the reasoning behind the agent's actions. Recent research has attempted to address this issue by using the guidance of pretrained neural agents to encode logic-based policies, allowing for interpretable decisions. A drawback of such approaches is the requirement of large amounts of predefined background knowledge in the form of predicates, limiting its applicability and scalability. In this work, we propose a novel approach, Explanatory Predicate Invention for Learning in Games (EXPIL), that identifies and extracts predicates from a pretrained neural agent, later used in the logic-based agents, reducing the dependency on predefined background knowledge. Our experimental evaluation on various games demonstrate the effectiveness of EXPIL in achieving explainable behavior in logic agents while requiring less background knowledge.

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。

↑