用高效模型强化学习，实现欠驱动系统全局控制。
Learning global control of underactuated systems with Model-Based Reinforcement Learning
- 基于模型强化学习，用仿真优化策略而非直接试错。
- 在真实机器人上实现摆杆与双摆系统的稳定控制。
- 适合研究数据效率高的机器人控制算法者参考。
本文介绍我们在ICRA 2025年举办的第三届「AI奥林匹克竞赛（RealAIGym）」中提出的解决方案。我们采用蒙特卡洛概率推断学习控制（MC-PILCO）这一模型增强型强化学习算法，该方法以极高的数据效率著称，适用于低维机器人任务，如倒立摆、球与板、弗鲁塔摆等。MC-PILCO通过交互数据优化系统动力学模型，并在模拟环境中迭代优化策略，避免了直接依赖真实系统数据的高成本。该方法在物理系统中表现优异，显著优于无模型方法。值得注意的是，MC-PILCO已连续赢得前两届该竞赛，证明其在仿真与真实环境中的鲁棒性。本文简要回顾算法原理，并重点讨论其在摆杆（pendubot）与双摆（acrobot）系统中实现全局控制的关键实现细节。
原文摘要 · Abstract (English)
This short paper describes our proposed solution for the third edition of the "AI Olympics with RealAIGym" competition, held at ICRA 2025. We employed Monte-Carlo Probabilistic Inference for Learning Control (MC-PILCO), an MBRL algorithm recognized for its exceptional data efficiency across various low-dimensional robotic tasks, including cart-pole, ball \& plate, and Furuta pendulum systems. MC-PILCO optimizes a system dynamics model using interaction data, enabling policy refinement through simulation rather than direct system data optimization. This approach has proven highly effective in physical systems, offering greater data efficiency than Model-Free (MF) alternatives. Notably, MC-PILCO has previously won the first two editions of this competition, demonstrating its robustness in both simulated and real-world environments. Besides briefly reviewing the algorithm, we discuss the most critical aspects of the MC-PILCO implementation in the tasks at hand: learning a global policy for the pendubot and acrobot systems.
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。