DeepRL-Agents
DeepRL-Agents copied to clipboard
awjuliani
A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
Before: ``` b = scipy.misc.imresize(a[:,:,0],[84,84,1],interp='nearest') c = scipy.misc.imresize(a[:,:,1],[84,84,1],interp='nearest') d = scipy.misc.imresize(a[:,:,2],[84,84,1],interp='nearest') a = np.stack([b,c,d],axis=2) ``` After: ``` a= (skimage.transform.resize(a,[84,84,3],order=0)*255).astype(np.uint8) ```
Code doesn't work in TF 2.0 and later. Compat mode looks possible, but for the same trouble a minor revision would fix it.
In Model-Network.ipynb garbage code. Should be removed. ``` input_data = tf.placeholder(tf.float32, [None, 5]) with tf.variable_scope('rnnlm'): softmax_w = tf.get_variable("softmax_w", [mH, 50]) softmax_b = tf.get_variable("softmax_b", [50]) ```
My problem is actually creating some buffer but what stoped me boils down to not being able to do two training session if it is the same buffer the first...
In the [notebook](https://github.com/awjuliani/DeepRL-Agents/blob/master/Deep-Recurrent-Q-Network.ipynb) I don't see where your recurrent Q value model gets its trace dimension. You're just reshaping the output of a convnet and feeding this directly into an...
From my understanding the target network updates are implemented wrong in the notebook Double-Dueling-DQN.ipynb. As it updates the same step as the main network (every 4th). In this simple environment...
Hi there, The number of available CPU threads in my machine should be 16. However, I tested the number of workers in CPU only A3C-Doom because I set, `import os...
In https://github.com/awjuliani/DeepRL-Agents/blob/master/Vanilla-Policy.ipynb, there's a comment: #Get our reward for taking an action given a bandit. That tutorial uses the CartPole-v0 environment right? I don't think there is a bandit in...
jupyter notebook says there's no name DoomGame() in line 17, last code block. Why is it happening?
