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 2204.05036cs.LGcs.AI
收藏

Pareto条件网络

Pareto Conditioned Networks

Vrije Universiteit Brussel(布鲁塞尔自由大学)

Mathieu Reymond, Eugenio Bargiacchi, Ann Nowé

摘要:

在多目标优化中,学习所有达到帕累托有效解的策略是一个昂贵的过程。最优策略的集合可以随着目标的数量呈指数级增长,并且恢复所有解决方案需要对整个状态空间进行详尽的探索。我们提出了帕累托条件网络(PCN),一种方法,使用一个单一的神经网络,以涵盖所有非支配的政策。PCN将过去的每一次过渡与其剧集的回归联系起来。它训练网络,使得当以相同的返回为条件时,它应该重演所述过渡。在此过程中,我们将优化问题转化为分类问题。我们恢复一个具体的政策,通过调节网络所需的帕累托有效的解决方案。我们的方法是稳定的,因为它以监督的方式学习,从而避免了移动目标的问题。此外,通过使用单个网络,PCN可以有效地扩展目标的数量。最后,它对Pareto前沿的形状做了最小的假设,这使得它比以前最先进的多目标强化学习算法适用于更广泛的问题。

英文摘要:

In multi-objective optimization, learning all the policies that reach Pareto-efficient solutions is an expensive process. The set of optimal policies can grow exponentially with the number of objectives, and recovering all solutions requires an exhaustive exploration of the entire state space. We propose Pareto Conditioned Networks (PCN), a method that uses a single neural network to encompass all non-dominated policies. PCN associates every past transition with its episode's return. It trains the network such that, when conditioned on this same return, it should reenact said transition. In doing so we transform the optimization problem into a classification problem. We recover a concrete policy by conditioning the network on the desired Pareto-efficient solution. Our method is stable as it learns in a supervised fashion, thus avoiding moving target issues. Moreover, by using a single network, PCN scales efficiently with the number of objectives. Finally, it makes minimal assumptions on the shape of the Pareto front, which makes it suitable to a wider range of problems than previous state-of-the-art multi-objective reinforcement learning 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。

↑