Recurrent neural networks for reinforcement learning: architecture, learning algorithms and internal representation
Recurrent neural networks for reinforcement learning: architecture, learning algorithms and internal representation
复制标题
用于强化学习的循环神经网络：架构、学习算法和内部表示
DOI：
10.1109/ijcnn.1998.687168
复制
发表时间：
1998
期刊：
影响因子：
--
通讯作者：
Y. Nishikawa
中科院分区：
文献类型：
--
作者：
Ahmet Onat;Hajime Kita;Y. Nishikawa
强化学习是一种自主代理的学习方案，允许代理找到采取行动的最佳策略，从而在未知环境中最大化标量强化信号。如果代理可以访问环境的整个状态，则将感官输入映射到操作的反应策略就足够了。然而，如果环境状态是部分可观察的，则需要使用过去的观察结果来创建动态策略的特殊方法。为了克服这个问题，作者提出了一种使用带有 Q 学习的循环神经网络作为学习代理的方法。论文通过计算机模拟比较了该方法的几种网络架构和学习算法。此外，使用聚类技术检查训练网络中的内部表示。它表明环境状态的表征在网络中得到了很好的发展。
Reinforcement learning is a learning scheme for an autonomous agent that allows the agent to find the optimal policy of taking actions which maximize a scalar reinforcement signal in unknown environments. If the agent has access to the whole state of the environment, a reactive policy which maps the sensory input to the action is sufficient. However, if the state of the environment is partially observable, special methods for creating a dynamic policy that utilizes the past observations are necessary. To overcome this problem, the authors have proposed a method using recurrent neural networks with Q-learning, as a learning agent. The paper compares several types of network architecture and learning algorithms for this method through computer simulation. Further, the internal representation in the trained networks is examined using a clustering technique. It shows that the representation of the environmental state is developed well in the networks.