arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.11293cs.LGcs.NE
收藏

潜空间中的进化规划

Evolutionary Planning in Latent Space

IT-University of Copenhagen(哥本哈根信息技术大学)

Thor V. A. N. Olesen, Dennis T. T. Nguyen, Rasmus Berg Palm, Sebastian Risi

摘要:

规划是强化学习的一种强大方法,具有几个理想的属性。然而,它需要一个世界的模型,这在许多现实生活中的问题是不容易得到的。在本文中,我们建议学习一个世界模型,使进化规划在潜在空间(EPLS)。我们使用变分自动编码器(VAE)来学习个体观测的压缩潜在表示,并扩展混合密度递归神经网络(MDRNN)来学习可用于规划的世界的随机多模态前向模型。我们使用随机突变爬山(RMHC)来寻找一系列的行动,最大限度地提高预期的回报,在这个学习模型的世界。我们演示了如何构建一个世界的模型,通过引导它与推出从一个随机的政策,并迭代地完善它与推出从一个越来越准确的规划政策,使用学习世界模型。经过几次迭代的改进后,我们的规划代理比标准的无模型强化学习方法更好,证明了我们方法的可行性。

英文摘要:

Planning is a powerful approach to reinforcement learning with several desirable properties. However, it requires a model of the world, which is not readily available in many real-life problems. In this paper, we propose to learn a world model that enables Evolutionary Planning in Latent Space (EPLS). We use a Variational Auto Encoder (VAE) to learn a compressed latent representation of individual observations and extend a Mixture Density Recurrent Neural Network (MDRNN) to learn a stochastic, multi-modal forward model of the world that can be used for planning. We use the Random Mutation Hill Climbing (RMHC) to find a sequence of actions that maximize expected reward in this learned model of the world. We demonstrate how to build a model of the world by bootstrapping it with rollouts from a random policy and iteratively refining it with rollouts from an increasingly accurate planning policy using the learned world model. After a few iterations of this refinement, our planning agents are better than standard model-free reinforcement learning approaches demonstrating the viability of our approach.

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。

↑