-
The RLLib converges slowly on a simple environment compared to comparable algorithms with different libraries under same conditions (see below the results). Is this something that is expected or is th…
-
**Important Note: We do not do technical support, nor consulting** and don't answer personal questions per email.
Please post your question on the [RL Discord](https://discord.com/invite/xhfNqQv), [R…
genkv updated
2 years ago
-
**Important Note: We do not do technical support, nor consulting** and don't answer personal questions per email.
Please post your question on the [RL Discord](https://discord.com/invite/xhfNqQv), [R…
-
### What happened + What you expected to happen
**What happened**
When I disable the preprocessor api and run on GPU. Then during training with my custom forward pass I get always tensors in my `i…
-
Greetings! I'm a PyTorch RL fan but previously used baselines and stable baselines for research. I notice stable-baselines3 through the origin stable-baselines issue.
Recently there are many PyTorch…
-
### 🐛 Bug
`model.learn()` fails with DQN agent when freeway environment is wrapped by `AtariWrapper()` with `noop_max=500`
### To Reproduce
Here is the minimal code to reproduce the problem:
…
-
Hello @abalakrishna123 @bthananjeyan
Thanks for sharing this repo. I read your paper [Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones](https://arxiv.org/pdf/2010.15920.pdf). T…
-
### 🐛 Bug
I was going through [stable baselines 3's first example code](https://stable-baselines3.readthedocs.io/en/master/guide/examples.html) and after I had downloaded the whole code into my not…
-
Such as DQN and A2C, the result is extremely bad with a reward of nearly 0. It makes me confused.
Other methods in stable baseline 3 do not support a discrete action space (e.g. SAC, TD3 ...).
-
### What is the problem?
When trying to train with a DQN (or really any other algorithm - I even tried it with PPO) with the latest nightly installation of Ray , I seem to get a weird error throw…