-
results on Pong seem to indicate that the experience replay functionality is not working correctly. Performance is terrible, and the agent is far worse than its vanilla alternative. The paper introduc…
-
Create a `.md` file to outline a roadmap for learning Generative AI, providing detailed information on the following topics:
- **Generative AI Models**: Overview and explanations of various generat…
-
- Implement Server api function call to Remove / Add train at specific location on a line.
- Implement interaction to drag trains off of and onto transport lines.
- Create an in-game interface to ad…
-
### Current Behavior
I have some core tasks that need to be run before running specs. I am using the `dependsOn` and `readyWhen` options with the aim of:
1. running 2 backend tasks in parallel (…
-
Hi , I run your train_agent file, but I only got 0.01 average reward after 3000 episodes run. Did not get the same results you said. I don't know why.
-
is there a reason why the agents were implemented this way?
any paper that proves that it gives an advantage over the "normal" method (if bought/sold true -> only close position or nothing)?
-
christmas came in july!!!
![image](https://media3.giphy.com/media/v1.Y2lkPTc5MGI3NjExdGZicGtzbmV4c3UxZmg0MjJxNWMwZXo3bHJsbDR0azI5dnBtYjM5dyZlcD12MV9pbnRlcm5hbF9naWZfYnlfaWQmY3Q9Zw/qgri3D9sTwCUGMcT8…
-
Hello. I really appreciate your tutorials, but now I am a little lost. My goal is to simply just use the trained VAE for the mountain track and have the agent start learning on the mountain track. I b…
-
When i do :
`python main.py --is_train=False --display=True --use_gpu=False`
I get :
`
[*] GPU : 1.0000
[2018-05-23 17:17:55,692] Making new env: Breakout-v0
{'_save_step': 500000,
'_test_ste…
-
Hi! I am trying to use the architecture you proposed in your paper. Although the idea was clearly expressed in the paper, I am very curious why the agent alpha and agent beta are different in design. …