arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2406.18924cs.AIcs.LGcs.RO
收藏

学习多目标连续机器人控制的 Pareto Set

Learning Pareto Set for Multi-Objective Continuous Robot Control

Southern University of Science and Technology(南方科技大学);Shenzhen University(深圳大学);City University of Hong Kong(香港城市大学)

Tianye Shu, Ke Shang, Cheng Gong, Yang Nan, Hisao Ishibuchi

AI总结:

提出一种资源高效的多目标强化学习算法,利用单个 hypernet 在高维参数空间学习 Pareto set 的连续表示,以最少的参数实现最佳性能。

摘要:

对于具有多个冲突目标的控制问题,存在一个被称为 Pareto set 的 Pareto 最优策略集合,而非单一最优策略。当多目标控制问题连续且复杂时,传统的多目标强化学习(MORL)算法需要搜索许多 Pareto 最优深度策略来近似 Pareto set,这非常消耗资源。在本文中,我们提出了一种简单且资源高效的 MORL 算法,该算法使用单个 hypernet 在高维策略参数空间中学习 Pareto set 的连续表示。学习到的 hypernet 可以直接为不同的用户偏好生成各种训练良好的策略网络。我们在七个多目标连续机器人控制问题上将我们的方法与两种最先进的 MORL 算法进行了比较。实验结果表明,我们的方法以最少的训练参数实现了最佳的整体性能。一个有趣的观察是,Pareto set 在高维参数空间中可以很好地由曲线或曲面来近似。这一观察将为研究人员设计新的 MORL 算法提供洞察。

英文摘要:

For a control problem with multiple conflicting objectives, there exists a set of Pareto-optimal policies called the Pareto set instead of a single optimal policy. When a multi-objective control problem is continuous and complex, traditional multi-objective reinforcement learning (MORL) algorithms search for many Pareto-optimal deep policies to approximate the Pareto set, which is quite resource-consuming. In this paper, we propose a simple and resource-efficient MORL algorithm that learns a continuous representation of the Pareto set in a high-dimensional policy parameter space using a single hypernet. The learned hypernet can directly generate various well-trained policy networks for different user preferences. We compare our method with two state-of-the-art MORL algorithms on seven multi-objective continuous robot control problems. Experimental results show that our method achieves the best overall performance with the least training parameters. An interesting observation is that the Pareto set is well approximated by a curved line or surface in a high-dimensional parameter space. This observation will provide insight for researchers to design new MORL algorithms.

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。

↑