A Memory-Based Reinforcement Learning Model Utilizing Macro-Actions
暂无分享,去创建一个
One of the difficulties in reinforcement learning (RL) is that an optimal policy is acquired through enormous trials. As a solution to reduce waste explorations in learning, recently the exploitation of macro-actions has been focused. In this paper, we propose a memory-based reinforcement learning model in which macro-actions are generated and exploited effectively. Through the experiments for two standard tasks, we confirmed that our proposed method could decrease waste explorations especially in the early training stage. This property contributes to enhancing training efficiency in RL tasks.
[1] John C. Platt. A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.
[2] Richard S. Sutton,et al. Roles of Macro-Actions in Accelerating Reinforcement Learning , 1998 .
[3] Richard S. Sutton,et al. Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.
[4] Shigeo Abe,et al. A Memory-Based Reinforcement Learning Algorithm to Prevent Unlearning in Neural Networks , 2004 .