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 2102.11394cs.LGcs.ROcs.SYeess.SYstat.ML
收藏

探索上下文:面向上下文条件动力学模型的最优数据收集

Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Jan Achterhold, Joerg Stueckler

AI总结:

针对参数化动力系统族的动力学建模问题,提出以潜上下文变量为条件的随机过程建模方法,通过引导系统经过高信息量转移实现有限交互下的最优探索,在玩具问题和强化学习环境中验证了有效性。

摘要:

本文研究针对属性各异的参数化动力系统族的动力学模型学习。这类动力学模型被构建为以潜上下文变量为条件的随机过程,该变量从对应系统的观测转移中推断得到。该概率建模框架使我们能够计算出一个动作序列,在环境交互次数有限的情况下,最优地探索参数化族内的给定系统,实现方式是引导系统经过对上下文变量信息量最大的转移。我们在一个非线性玩具问题和两个知名强化学习环境上验证了该探索方法的有效性。

英文摘要:

In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from observed transitions of the respective system. The probabilistic formulation allows us to compute an action sequence which, for a limited number of environment interactions, optimally explores the given system within the parametrized family. This is achieved by steering the system through transitions being most informative for the context variable. We demonstrate the effectiveness of our method for exploration on a non-linear toy-problem and two well-known reinforcement learning environments.

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。

↑