-
### 🐛 Bug
Further to the [issue I brought up here](https://github.com/openai/gym/issues/3148) over at Gym, I seem to be having some issues getting the `Dict` observation space to "work" properly.
…
-
I'm a PhD student studying RL. I've really loved using wandb, and I particularly find the sweep API to be a convenient way to setup runs. I've run into a problem recently when I tried to scale up.
…
-
The agent should be able to perform better. To achieve that we should
- experiment with more algorithms than just PPO and
- increase the complexity of the hyperparameter search space (i.e. including…
-
If you have any questions, feel free to create an issue with the tag [question].
If you wish to suggest an enhancement or feature request, add the tag [feature request].
If you are submitting a …
-
具体报错信息如下:
[10-04 22:17:16 MainThread @logger.py:242] Argv: train.py
[10-04 22:17:16 MainThread @utils.py:73] paddlepaddle version: 2.3.2.
[10-04 22:17:16 MainThread @__init__.py:27] Have found envi…
-
Breath with Ubuntu/gnome. I get the Dummy Output with stock install, tried `sof-setup-audio` and `SOUNDCARD=rtk sof-setup-audio`, which remove the Dummy Output, but do not install a working driver. Th…
-
### 🐛 Bug
Using the [HParam logger for Tensorboard](https://stable-baselines3.readthedocs.io/en/master/guide/tensorboard.html#logging-hyperparameters), if, in a new run, I add a new hyperparameter …
-
Hello! Wonderful repository for playing with montezuma's revenge with an algorithm that works! :) :)
I am having a little bit of trouble getting it to run. After installing everything, I am runnin…
-
I have been experimenting with TD3 using a callback function that does an evaluation of the model every thousand timesteps. It seems that when using TD3 the evaluation of the model gives always the sa…
-
hello
I try to solve an AI problem related to a graph using RL and stable baselines.
but it seems like the RL model cannot understand and communicate with the graph at all and even fail in simple ta…