arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.08684cs.LGcs.ROcs.SYeess.SYstat.ML
收藏

通过乐观策略搜索和规划的高效基于模型的强化学习

Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planning

ETH Zurich(苏黎世联邦理工学院);Bosch Center for Artificial Intelligence(博世人工智能中心)

Sebastian Curi, Felix Berkenkamp, Andreas Krause

摘要:

具有概率动态模型的基于模型的强化学习算法是数据效率最高的学习方法之一。这通常归因于他们区分认知和任意不确定性的能力。然而,大多数算法在学习模型时区分这两种不确定性,但在优化策略时却忽略了这两种不确定性,导致了贪婪和探索不足。同时,乐观探索算法还没有实用的求解器。在本文中,我们提出了一个实用的乐观探索算法(H-UCRL)。H-UCRL重新参数化的一组合理的模型和幻觉控制直接对认知的不确定性。通过用幻觉输入扩充输入空间,可以使用标准贪婪规划器来求解H-UCRL。此外,我们分析了H-UCRL,并构造了一个一般的遗憾界校准模型,这是可证明的高斯过程模型的情况下,是次线性的。基于这一理论基础,我们展示了乐观探索如何轻松地与最先进的强化学习算法和不同的概率模型相结合。我们的实验表明,乐观的探索显着加快学习时,有惩罚的行动,这是众所周知的困难,现有的基于模型的强化学习算法的设置。

英文摘要:

Model-based reinforcement learning algorithms with probabilistic dynamical models are amongst the most data-efficient learning methods. This is often attributed to their ability to distinguish between epistemic and aleatoric uncertainty. However, while most algorithms distinguish these two uncertainties for learning the model, they ignore it when optimizing the policy, which leads to greedy and insufficient exploration. At the same time, there are no practical solvers for optimistic exploration algorithms. In this paper, we propose a practical optimistic exploration algorithm (H-UCRL). H-UCRL reparameterizes the set of plausible models and hallucinates control directly on the epistemic uncertainty. By augmenting the input space with the hallucinated inputs, H-UCRL can be solved using standard greedy planners. Furthermore, we analyze H-UCRL and construct a general regret bound for well-calibrated models, which is provably sublinear in the case of Gaussian Process models. Based on this theoretical foundation, we show how optimistic exploration can be easily combined with state-of-the-art reinforcement learning algorithms and different probabilistic models. Our experiments demonstrate that optimistic exploration significantly speeds-up learning when there are penalties on actions, a setting that is notoriously difficult for existing model-based reinforcement learning algorithms.

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。

↑