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 2008.05598cs.LGcs.AI
收藏

高维问题的深度基于模型的强化学习综述

Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey

Leiden Institute of Advanced Computer Science(莱顿高级计算机科学研究所)

Aske Plaat, Walter Kosters, Mike Preuss

摘要:

深度强化学习在过去几年中取得了显著的成功。高度复杂的顺序决策问题已经在游戏和机器人等任务中得到解决。不幸的是,大多数深度强化学习方法的样本复杂度都很高,这阻碍了它们在一些重要应用中的使用。基于模型的强化学习创建环境动态的显式模型以减少对环境样本的需求。当前的深度学习方法使用高容量网络来解决高维问题。不幸的是,高容量模型通常需要许多样本,从而否定了基于模型的方法中较低样本复杂性的潜在好处。因此,基于深度模型的方法面临的挑战是在保持低样本复杂度的同时实现高预测能力。近年来,许多基于模型的方法被引入来解决这一挑战。在本文中,我们调查了当代基于模型的景观。首先,我们讨论定义和与其他领域的关系。我们提出了一个分类法的基础上,三种方法:使用明确的规划给定的过渡,使用明确的规划学习的过渡,规划和过渡的端到端的学习。我们使用这些方法来组织一个全面的概述最近的重要发展,如潜在的模型。我们描述的方法和基准,我们建议的每一种方法的未来工作的方向。其中有前途的研究方向是课程学习,不确定性建模,并使用潜在的模型迁移学习。

英文摘要:

Deep reinforcement learning has shown remarkable success in the past few years. Highly complex sequential decision making problems have been solved in tasks such as game playing and robotics. Unfortunately, the sample complexity of most deep reinforcement learning methods is high, precluding their use in some important applications. Model-based reinforcement learning creates an explicit model of the environment dynamics to reduce the need for environment samples. Current deep learning methods use high-capacity networks to solve high-dimensional problems. Unfortunately, high-capacity models typically require many samples, negating the potential benefit of lower sample complexity in model-based methods. A challenge for deep model-based methods is therefore to achieve high predictive power while maintaining low sample complexity. In recent years, many model-based methods have been introduced to address this challenge. In this paper, we survey the contemporary model-based landscape. First we discuss definitions and relations to other fields. We propose a taxonomy based on three approaches: using explicit planning on given transitions, using explicit planning on learned transitions, and end-to-end learning of both planning and transitions. We use these approaches to organize a comprehensive overview of important recent developments such as latent models. We describe methods and benchmarks, and we suggest directions for future work for each of the approaches. Among promising research directions are curriculum learning, uncertainty modeling, and use of latent models for transfer learning.

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。

↑