-
@eleurent Hi eleurent, sorry to bother you again. I am not sure you receive my yesterday question or not. So I want to try again.
With your help, now I can train and test the Highway-env with DQN. H…
-
I have been having issues with processes dying from memory exhaustion. I instrumented to code to figure out the rate of consumption and got the following image:
![memory-profile](https://user-images.…
-
Most of the time people use image as input to train a deep neural network to play Doom, anyone thinking about using real number info(position of player/medkit/enemy/ammo) as a vector to train a deep n…
-
No matter whether baseline is used, ` PolicyGradientModel.reward_estimation ` computes cumulative rewards in one batch by using ` util.cumulative_discount ` with ` cumulative_start=0.0 ` .
In my op…
-
Please help me understand why the previous state is always equal to the next state ?
if thats the case how will any NN will work on state.
```
import numpy as np
from q_learning.utils import Sca…
-
Hi,
I have started using this on Lunar-Lander-v2 which is not continuous and I do not yet see convergence.
Did this code converged you were testing?
Also for training these simple cases, did you …
-
My next step is to have clean working and benchmarked policy gradient reinforcement learning algorithms.
-
The introduction of *NoisyNets* appears to add significant explorative capability to DQN & A3C, in some cases making progress on tasks that had otherwise exhibited little advancement.
I wasn't sure…
-
On the latest AWS DL AMI, I get strange errors trying to install ray from source. Not sure how to debug them:
```
Replacing /home/ubuntu/anaconda3/envs/tensorflow_p36/lib/python3.6/site-packages…
-
HI, I spent some time looking over the guided_a3c example, documentation and reading the code for the BTgymRandomDataDomain class, and my question is: if I want to use pandas.resample() function and d…