Chaos-Based Reinforcement Learning When Introducing Refractoriness in Each Neuron
Chaos-Based Reinforcement Learning When Introducing Refractoriness in Each Neuron
复制标题
在每个神经元中引入不应性时基于混沌的强化学习
DOI：
10.1007/978-981-13-7780-8_7
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Katsuki Sato and Katsunari Shibata
中科院分区：
文献类型：
--
作者：
Kenta Fujisawa;Shudai Ishikawa;Ryosuke Kubota;Katsuki Sato and Katsunari Shibata
针对“思考”的出现，我们提出了一种新的使用混沌神经网络的强化学习。然后我们建立了一个假设，内部的混沌动力学通过学习成长为“思考”。在我们之前的工作中，强循环连接权产生内部混沌动力学。另一方面，混沌动力学通常是通过在每个神经元中引入耐火度而产生的。耐火性是在生物神经元中观察到的放电神经元在一段时间内变得不敏感的特性。在基于混沌的强化学习中，在每个神经元中引入了耐火度。结果表明，通过本文提出的基于混沌的强化学习方法，网络可以学习简单的目标到达任务。与无耐火度的情况相比，它可以用更小的循环连接权进行学习。通过引入耐火度，药剂行为变得更具探索性，在相同的循环权值范围内，Lyapunov指数变得更大。
Aiming for the emergence of “thinking”, we have proposed new reinforcement learning using a chaotic neural network. Then we have set up a hypothesis that the internal chaotic dynamics would grow up into “thinking” through learning. In our previous works, strong recurrent connection weights generate internal chaotic dynamics. On the other hand, chaotic dynamics are often generated by introducing refractoriness in each neuron. Refractoriness is the property that a firing neuron becomes insensitive for a while and observed in biological neurons. In this paper, in the chaos-based reinforcement learning, refractoriness is introduced in each neuron. It is shown that the network can learn a simple goal-reaching task through our new chaos-based reinforcement learning. It can learn with smaller recurrent connection weights than the case without refractoriness. By introducing refractoriness, the agent behavior becomes more exploratory and Lyapunov exponent becomes larger with the same recurrent weight range.