TensorLayer
TensorLayer copied to clipboard
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
### Issue Description When I use the tensor output from TensorFlow to pass to the tl layer, an error will be reported AttributeError: 'tensorflow.python.framework.ops.EagerTensor' object has no attribute '_info' ###...
在[中文版](https://deepreinforcementlearningbook.org/assets/pdfs/%E6%B7%B1%E5%BA%A6%E5%BC%BA%E5%8C%96%E5%AD%A6%E4%B9%A0(%E4%B8%AD%E6%96%87%E7%89%88-%E5%BD%A9%E8%89%B2%E5%8E%8B%E7%BC%A9).pdf)的 `2.3.2 马尔可夫奖励过程` 中介绍了 `价值函数(Value Function)V (s)`,书中是这么说的: > 价值函数(Value Function)V(s) 是状态 s 的期望回报(Expected Return)。 > > 一种估计价值 V (s) 的简单方法是蒙特卡罗法,给定一个状态 s,我们用状态转移矩阵 P 随机采样大量的轨迹,来求近似期望。 > > 除了蒙特卡罗方法,还有很多方法可以用来计算 V (s),比如贝尔曼期望方程(Bellman Expectation Equation)、逆矩阵方法(Inverse...
### New Issue Checklist - [ Yes ] I have read the [Contribution Guidelines](https://github.com/tensorlayer/tensorlayer/blob/master/CONTRIBUTING.md) - [ Yes ] I searched for [existing GitHub issues](https://github.com/tensorlayer/tensorlayer/issues) ### Issue Description [INSERT DESCRIPTION OF...
_**_a = np.argmax(Q[s, :] + np.random.randn(1, env.action_space.n) * (1. / (i + 1))) IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices_**_...
### New Issue Checklist - [x] I have read the [Contribution Guidelines](https://github.com/tensorlayer/tensorlayer/blob/master/CONTRIBUTING.md) - [x] I searched for [existing GitHub issues](https://github.com/tensorlayer/tensorlayer/issues) ### Issue Description [INSERT DESCRIPTION OF THE PROBLEM] ### Reproducible...
### Checklist - [x ] I've tested that my changes are compatible with the latest version of Tensorflow. - [x ] I've read the [Contribution Guidelines](https://github.com/tensorlayer/tensorlayer/blob/master/CONTRIBUTING.md) - [x ] I've...