-
Hey Haris,
I am having trouble with making Rllib work with a custom model. Here is a link to their documentation:
https://docs.ray.io/en/master/rllib-models.html?highlight=tfmodelv2#custom-models-…
-
Do you intend to work on meta-RL any time soon?
In order to better train an agent that interacts with a world, the basic idea involves building an RNN capable of keeping track of the particularitie…
-
### Task 4.1: Mine GitHub Datasets
1. Write a Python script that will go through the list here
[INITIAL_PYTHON_REPOS_GITHUB.xlsx](https://github.com/paser-group/MLForensics/files/5514538/INITIA…
-
Hello,
I just installed conx and my tensorflow version is 2.4.0.
When I try to import conx with import conx as cx, I get the follow error message.
-------------------------------------------…
-
Hello!
Out of the box the solution is not working. As I appreciate your work very much, a definition of used pip versions would be very helpful to contribute to your project
-
python main.py --mode train --order offset --model_path model --method RL
是可以执行成功的。
但是eval 的时候报错。
python main.py --mode eval --order offset --model_path model --method RL
root@:/data/DCA$ …
-
### What happened + What you expected to happen
Using an observation space where the space is a gym Dict, with both a Box and Discrete space inside the Dict (see reproduction script below), throws th…
-
Hi.
First, Thank you very much for sharing this project. It is absolutely amazing.
The custom training loop doesn't set Keras's backend training phase (training and testing). which makes the imple…
-
when you run examples/rl/deep_q_network_breakout.py, you will find that the memory leak. even when the buff reach its max lenght (max_memory_length), memory still will increase.
-
Hello, I'm studying with the book and i'm trying to implement my own environment inheriting from gym, and with a one-dimensional input works fine, similar to the CartPole-v1 example
But in this cas…