arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.00030cs.AI
收藏

基于策略感知的策略梯度方法模型学习

Policy-Aware Model Learning for Policy Gradient Methods

University of Toronto(多伦多大学);the Vector Institute(向量研究所);Google Research(谷歌研究院)

Romina Abachi, Mohammad Ghavamzadeh, Amir-massoud Farahmand

摘要:

研究了基于基于模型的强化学习(MBRL)中的模型学习问题。我们研究了MBRL算法的规划模块如何使用该模型,并建议模型学习模块应将规划者使用该模型的方式。这与传统的模型学习方法(例如基于最大似然估计的那些方法)形成对比,传统的模型学习方法在不明确考虑模型和规划器的交互的情况下学习环境的预测模型。我们专注于策略梯度类型的规划算法,并推导出新的损失函数的模型学习,将如何规划器使用的模型。我们称这种方法为策略感知模型学习(PAML)。理论上分析了一种通用的基于模型的策略梯度算法,并为优化后的策略提供了收敛性保证。我们还实证评估PAML的一些基准问题,显示出可喜的成果。

英文摘要:

This paper considers the problem of learning a model in model-based reinforcement learning (MBRL). We examine how the planning module of an MBRL algorithm uses the model, and propose that the model learning module should incorporate the way the planner is going to use the model. This is in contrast to conventional model learning approaches, such as those based on maximum likelihood estimate, that learn a predictive model of the environment without explicitly considering the interaction of the model and the planner. We focus on policy gradient type of planning algorithms and derive new loss functions for model learning that incorporate how the planner uses the model. We call this approach Policy-Aware Model Learning (PAML). We theoretically analyze a generic model-based policy gradient algorithm and provide a convergence guarantee for the optimized policy. We also empirically evaluate PAML on some benchmark problems, showing promising results.

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。

↑