Accuracy-based Curriculum Learning in Deep Reinforcement Learning
Accuracy-based Curriculum Learning in Deep Reinforcement Learning
复制标题
DOI：
--
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Pierre Fournier;Olivier Sigaud;M. Chetouani;Pierre-Yves Oudeyer
中科院分区：
文献类型：
--
作者：
Pierre Fournier;Olivier Sigaud;M. Chetouani;Pierre-Yves Oudeyer
本文研究了一种新的基于精确度要求自适应选择的自动化课程学习形式--基于精确度的课程学习。使用基于深度确定性策略梯度算法的强化学习代理，并针对Reacher环境，我们首先证明了随机抽样的各种精度要求训练的代理比被要求始终非常准确的代理学习效率更高。然后，我们证明了基于能力进步的局部测量的精确度要求的适应性选择，自动生成难度逐渐增加的课程，从而产生比随机抽样更好的学习效率。
In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a reinforcement learning agent based on the Deep Deterministic Policy Gradient algorithm and addressing the Reacher environment, we first show that an agent trained with various accuracy requirements sampled randomly learns more efficiently than when asked to be very accurate at all times. Then we show that adaptive selection of accuracy requirements, based on a local measure of competence progress, automatically generates a curriculum where difficulty progressively increases, resulting in a better learning efficiency than sampling randomly.