Reward-Based Learning of a Memory-Required Task Based on the Internal Dynamics of a Chaotic Neural Network
Reward-Based Learning of a Memory-Required Task Based on the Internal Dynamics of a Chaotic Neural Network
复制标题
基于混沌神经网络内部动力学的记忆任务的奖励学习
DOI：
10.1007/978-3-319-46687-3_42
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Toshitaka Matsuki and Katsunari Shibata
中科院分区：
文献类型：
--
作者：
Nakagiri;N.,;Ohashi M.;Okada;R.;Ikeno;H.;Asaki Saito;Toshitaka Matsuki and Katsunari Shibata
我们期望通过使用混沌神经网络（NN）的强化学习（RL）框架中的探索增长，出现诸如“思考”之类的动态高级功能。在该框架中，混沌内部动力学用于探索，从而消除了外部探索噪声的必要性。一个特殊的RL方法已经提出了这个框架中的“痕迹”。另一方面，水库计算已经显示出其优秀的学习动态模式的能力。Hoerzer等人表明，学习可以通过给予奖励和探索噪音来完成，而不是明确的教师信号。在本文中，旨在将学习能力引入到我们的新RL框架中，证明了Hoerzer等人的工作中需要记忆的任务可以通过利用混沌内部动力学来学习，而不给探索噪声，同时灵活自主地调整探索水平。该任务也可以使用“痕迹”来学习，但仍然存在问题。
We have expected that dynamic higher functions such as “thinking” emerge through the growth from exploration in the framework of reinforcement learning (RL) using a chaotic Neural Network (NN). In this frame, the chaotic internal dynamics is used for exploration and that eliminates the necessity of giving external exploration noises. A special RL method for this framework has been proposed in which “traces” were introduced. On the other hand, reservoir computing has shown its excellent ability in learning dynamic patterns. Hoerzer et al. showed that the learning can be done by giving rewards and exploration noises instead of explicit teacher signals. In this paper, aiming to introduce the learning ability into our new RL framework, it was shown that the memory-required task in the work of Hoerzer et al. could be learned without giving exploration noises by utilizing the chaotic internal dynamics while the exploration level was adjusted flexibly and autonomously. The task could be learned also using “traces”, but still with problems.