arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.08070cs.ROcs.NE
收藏

面向开放式机器人问题的多目标学习算法

Multi-Objective Algorithms for Learning Open-Ended Robotic Problems

Universite De Sherbrooke(舍布鲁克大学);Menya AI division(Menya人工智能部门);Levio(Levio公司)

Martin Robert, Simon Brodeur, Francois Ferland

AI总结:

针对四足机器人运动中的训练不稳定和样本效率低问题,提出利用多目标进化算法作为自动课程学习机制的MOL方法,在MuJoCo中显著提升了稳定性和适应性。

摘要:

四足运动是一个复杂的开放式问题,对扩展自动驾驶车辆的适用范围至关重要。传统的强化学习方法常因训练不稳定性和样本效率低下而表现不佳。我们提出了一种新方法,利用多目标进化算法作为自动课程学习机制,并将其命名为Multi-Objective Learning (MOL)。该方法通过将速度指令投影到目标空间,并同时优化性能与多样性,显著提升了学习过程。在MuJoCo物理模拟器中测试表明,与基线方法相比,我们的方法展现出更优的稳定性和适应性。在基于均匀评估和定制评估的困难场景中,它分别比我们最佳的基线算法减少了19%和44%的错误。本研究为训练四足机器人引入了一个稳健的框架,为机器人运动和开放式机器人问题带来了显著的进步。

英文摘要:

Quadrupedal locomotion is a complex, open-ended problem vital to expanding autonomous vehicle reach. Traditional reinforcement learning approaches often fall short due to training instability and sample inefficiency. We propose a novel method leveraging multi-objective evolutionary algorithms as an automatic curriculum learning mechanism, which we named Multi-Objective Learning (MOL). Our approach significantly enhances the learning process by projecting velocity commands into an objective space and optimizing for both performance and diversity. Tested within the MuJoCo physics simulator, our method demonstrates superior stability and adaptability compared to baseline approaches. As such, it achieved 19\% and 44\% fewer errors against our best baseline algorithm in difficult scenarios based on a uniform and tailored evaluation respectively. This work introduces a robust framework for training quadrupedal robots, promising significant advancements in robotic locomotion and open-ended robotic problems.

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。

↑