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 2005.06800cs.LGstat.ML
收藏

基于模型的强化学习中的上下文感知动力学泛化模型

Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning

UC Berkeley(加州大学伯克利分校);KAIST(韩国科学技术院);Google Brain(谷歌大脑);University of Michigan Ann Arbor(密歇根大学安娜堡分校)

Kimin Lee, Younggyo Seo, Seunghyun Lee, Honglak Lee, Jinwoo Shin

摘要:

基于模型的强化学习(RL)通过学习环境的动态模型而享有若干益处,例如数据效率和规划。然而,学习可以概括不同动态的全局模型是一项具有挑战性的任务。为了解决这个问题,我们将学习全局动力学模型的任务分解为两个阶段:(a)学习捕获局部动态的上下文潜在向量,然后(b)预测以其为条件的下一状态。为了将动态特定信息编码到上下文潜在向量中,我们引入了一种新的损失函数,其鼓励上下文潜在向量对于预测前向和后向动态都是有用的。所提出的方法实现了优越的泛化能力,在各种模拟机器人和控制任务,相比现有的RL计划。

英文摘要:

Model-based reinforcement learning (RL) enjoys several benefits, such as data-efficiency and planning, by learning a model of the environment's dynamics. However, learning a global model that can generalize across different dynamics is a challenging task. To tackle this problem, we decompose the task of learning a global dynamics model into two stages: (a) learning a context latent vector that captures the local dynamics, then (b) predicting the next state conditioned on it. In order to encode dynamics-specific information into the context latent vector, we introduce a novel loss function that encourages the context latent vector to be useful for predicting both forward and backward dynamics. The proposed method achieves superior generalization ability across various simulated robotics and control tasks, compared to existing RL schemes.

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。

↑