使用神经网络在线估算Q-Table(Estimate Q-Table online with a neural network)
当我在强化学习中使用Q-Table进行保存状态动作时,某些状态从未(或很少)发生且状态动作值保持为零直到最大迭代,因此我决定使用神经网络在线估计Q-Table而不是使用Q-表。
哪种类型的神经网络可以更准确地估计这类问题,这个解决方案对我有帮助吗?
When i use Q-Table for save state-action in reinforcement learning, some state never (or rarely) happen and state-action value remain zero until max-iteration so i decide to estimate Q-Table online with a neural network instead of using Q-Table.
Which type of neural networks can estimate this kind of problem more accurate and does this solution help me?
最满意答案
我使用Localy加权回归(LWR)作为函数逼近,并简单地用此函数替换表
i use Localy Weighted Regression(LWR) as function approximation and simply replace table with this function
更多推荐
发布评论