arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.02057cs.LGstat.ML
收藏

离散到深度的监督策略学习

Discrete-to-Deep Supervised Policy Learning

Federation University(联邦大学);Defence Science and Technology Group(国防科学技术集团);Deakin University(迪肯大学)

Budi Kurniawan, Peter Vamplew, Michael Papasimeon, Richard Dazeley, Cameron Foale

摘要:

神经网络是一种有效的函数逼近器,但由于样本之间的相关性,很难在强化学习(RL)环境中进行训练。多年来,学者们通过使用经验重放或异步并行代理系统来解决这个问题。本文提出了用于在RL中训练神经网络的离散到深度监督策略学习(D2 D-SPL)。D2 D-SPL将连续状态空间离散为离散状态,并使用actor-critic来学习策略。然后,它从每个离散状态中选择一个输入值和具有最高数值偏好的动作作为输入/目标对。最后,它使用输入/目标对从所有离散状态训练分类器。D2 D-SPL使用单个代理,不需要经验重放,并且比最先进的方法学习得更快。我们测试我们的方法与两个RL环境,Cartpole和飞机操纵模拟器。

英文摘要:

Neural networks are effective function approximators, but hard to train in the reinforcement learning (RL) context mainly because samples are correlated. For years, scholars have got around this by employing experience replay or an asynchronous parallel-agent system. This paper proposes Discrete-to-Deep Supervised Policy Learning (D2D-SPL) for training neural networks in RL. D2D-SPL discretises the continuous state space into discrete states and uses actor-critic to learn a policy. It then selects from each discrete state an input value and the action with the highest numerical preference as an input/target pair. Finally it uses input/target pairs from all discrete states to train a classifier. D2D-SPL uses a single agent, needs no experience replay and learns much faster than state-of-the-art methods. We test our method with two RL environments, the Cartpole and an aircraft manoeuvring simulator.

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。

↑