-
I have just discovered that we did not have an issue for this thing we've been working on for a while now, so I'll create one to document progress.
- [ ] Week 1 (#235, #236, #277, #278, #280; `prim…
dniku updated
4 years ago
-
I'm trying to use rlpyt with my custom env with a non-image input state. For that, I first want to test it on a simple env, like CartPole-v0. And I use DQN and DqnAgent. But I get this error:
```
Tr…
-
Hi
in the stable-baselines implementation, HER does not support prioritized replay buffer. In the HER Paper they state that: "Prioritized experience replay (....) is orthogonal to our work and bot…
-
### What is the problem?
Ray: 0.8.4
Tensorflow: 1.14
RLLib is using its own checkpoint saving API instead of tensorflow's, and this API is not saving AdamOptimizer's momentum and accumulat…
-
Hi @astooke I am trying to write some code that will show how to save and load models for *resuming training* (not just for inference). Assuming we have algorithms that use replay buffers, this may re…
-
@eleurent Hi eleurent, I am very interested in your work. Since I am a beginner of Python, I have some problems to run this toolbox. Hope you can help me! Thanks in advance.
When I run this line in…
-
### Describe the problem
Currently we only have a simple pytorch example for A3C. It should be possible to "port" a bunch of pytorch algorithms onto the TorchPolicyGraph class and get them basicall…
ericl updated
4 years ago
-
The affinity stuff was a bit confusing, I wasn't able to figure out how to correctly set it up for using multiple GPUs for optimization. Note that I am doing only a single run. Here's my setup:
```…
-
## ❓ Questions & Help
Hi, my dataset size is 32. I only want to create one batch and feed them all to my network. How could I do it? Thank you so much.
-
Currently I want to rebuild the stable baseline model in keras and pytorch. It seems that the model cannot directly save to a h5 file. Thus I want to rebuild from the zip file save in this code.
```p…