-
Hi,
I am currently encountering some issues while trying to implement RORL，here is the problems：
1. The training time for RORL seems to be quite long (due to the additional calculation of 3 los…
-
I really like the thought process behind this. Nice idea.
-
### Describe the bug
UR10 reach can be trained with RSL_RL but not with RL_GAMES and SKRL.
### Steps to reproduce
Please try to provide a minimal example to reproduce the bug. Error message…
-
### ❓ Question
I want to use soft actor-critic in an environment with continuous state and action spaces. The environment is implemented in a `gym.Env` class with state and action spaces of the type …
-
I want to reproduce evalution only results using final checkpoints you provided.
I replaced policy_lm section with the checkpoint path in the default.yaml.
The following error occurs when loading…
-
A clear metric should be given for every user to determine this status for greater transparency.
-
Please make sure that this is a bug. As per our
[GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md),
we only address code/doc bugs, performance issues, feature requests a…
ghost updated
8 months ago
-
First, thank you very much for this wonderful package.
Visualization of loss trends gives us an indication of where the training process is bound for.
Where TD3 is concerned, i think that ther…
-
Hey all! I'm trying to track down a seeming reproducibility issue I'm having with the PPO implementation after I added some simple WandB logging. I ran the same code 7 times, and 4 of the times the re…
-
Hi!
I am using ray 1.2.0 and Python 3.6 on Ubuntu 18.04
I am trying a centralised critic PPO for the waterworld environment from Pettingzoo[sisl] [https://www.pettingzoo.ml/sisl/waterworld](url).
…