A reinforcement learning algorithm for neural networks with incremental learning ability
A reinforcement learning algorithm for neural networks with incremental learning ability
复制标题
一种具有增量学习能力的神经网络强化学习算法
DOI：
10.1109/iconip.2002.1201958
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
S. Abe
中科院分区：
文献类型：
--
作者：
N. Shiraga;S. Ozawa;S. Abe
当神经网络用于近似强化学习（RL）代理的动作值时，增量学习引起的“干扰”可能是严重的。为了解决这一问题，本文将一种具有增量学习能力的神经网络模型应用于强化学习问题。在该模型中，正确获取的输入输出关系被存储到长期记忆中，记忆的数据被有效地召回，以抑制干扰。为了评估增量学习能力，该模型被应用到两个问题：扩展的随机行走任务和扩展的山地车任务。在这些任务中，代理的工作空间随着学习的进行而扩展。在仿真中，我们证明了所提出的模型可以获得适当的动作值相比，以下三种方法的动作值函数的近似：瓦片编码，传统的神经网络模型和以前提出的神经网络模型。
When neural networks are used for approximating action-values of Reinforcement Learning (RL) agents, the "interference" caused by incremental learning can be serious. To solve this problem, in this paper, a neural network model with incremental learning ability was applied to RL problems. In this model, correctly acquired input-output relations are stored into long-term memory, and the memorized data are effectively recalled in order to suppress the interference. In order to evaluate the incremental learning ability, the proposed model was applied to two problems: Extended Random-Walk Task and Extended Mountain-Car Task. In these tasks, the working space of agents is extended as the learning proceeds. In the simulations, we certified that the proposed model could acquire proper action-values as compared with the following three approaches to the approximation of action-value functions: tile coding, a conventional neural network model and the previously proposed neural network model.
使用模块化神经网络检测未知环境的气体泄漏声音。
DOI：
--
发表时间：
2004
期刊：
Neurocomputing 62C
影响因子：
--
作者：
Manabu KOTANI;Seiichi OZAWA
通讯作者：
Seiichi OZAWA