Emergence of Higher Exploration in Reinforcement Learning Using a Chaotic Neural Network
Emergence of Higher Exploration in Reinforcement Learning Using a Chaotic Neural Network
复制标题
使用混沌神经网络进行强化学习的高级探索的出现
DOI：
10.1007/978-3-319-46687-3_5
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Yuki Goto and Katsunari Shibata
中科院分区：
文献类型：
--
作者：
T. Miyano;K. Cho;吉木綜一郎，田中 駿，堀内匡，幸田憲明;Yuki Goto and Katsunari Shibata
针对“逻辑思维”等高级功能的出现，我们小组提出了一种全新的强化学习，这种学习基于混沌神经网络的内部动力学进行探索。在避障任务的学习中，考察了在通过学习增长动力的过程中，探索水平从“低”到“高”的变化，即从“运动水平”到“更抽象的水平”。结果表明，智能体在躲避障碍物的同时学习到达目标，并且存在一个智能体看起来随机穿过障碍物右侧或左侧的区域。结果表明，尽管随着学习的进行，智能体有时会与障碍物相撞并被困一段时间，但仍有可能进行更高层次的探索。
Aiming for the emergence of higher functions such as “logical thinking”, our group has proposed completely novel reinforcement learning where exploration is performed based on the internal dynamics of a chaotic neural network. In this paper, in the learning of an obstacle avoidance task, it was examined that in the process of growing the dynamics through learning, the level of exploration changes from “lower” to “higher”, in other words, from “motor level” to “more abstract level”. It was shown that the agent learned to reach the goal while avoiding the obstacle and there is an area where the agent looks to pass through the right side or left side of the obstacle randomly. The result shows the possibility of the “higher exploration” though the agent sometimes collided with the obstacle and was trapped for a while as learning progressed.