通过分治状态表示设计简单课程，显著提升强化学习策略的鲁棒性。
Curricula for Learning Robust Policies with Factored State Representations in Changing Environments
- 基于状态分治表示，按高后悔值变量设计训练课程
- 实验表明课程策略使策略鲁棒性明显增强
- 适合在动态复杂环境中训练鲁棒策略的研究者参考
稳健策略使强化学习智能体能够有效适应并运行在不可预测、动态且不断变化的真实世界环境中。分治表示将复杂的状态和动作空间分解为独立的组件，可提升策略学习中的泛化能力和样本效率。本文探讨了使用分治状态表示的智能体其训练课程对所学策略鲁棒性的影响。实验验证了三种简单课程的有效性，例如仅在每轮中改变后悔值最高的变量，这些课程能显著提升策略鲁棒性，为复杂环境下的强化学习提供了实用洞见。
原文摘要 · Abstract (English)
Robust policies enable reinforcement learning agents to effectively adapt to and operate in unpredictable, dynamic, and ever-changing real-world environments. Factored representations, which break down complex state and action spaces into distinct components, can improve generalization and sample efficiency in policy learning. In this paper, we explore how the curriculum of an agent using a factored state representation affects the robustness of the learned policy. We experimentally demonstrate three simple curricula, such as varying only the variable of highest regret between episodes, that can significantly enhance policy robustness, offering practical insights for reinforcement learning in complex environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。