Eleni Nisioti

[RLlib] Ape-X crashes for custom environment with Dict observation space

1

### What happened + What you expected to happen I am trying to run Ape-X following the example [here](https://github.com/ray-project/ray/issues/18034) for the [Wordcraft environemnt](https://github.com/minqi/wordcraft). I have taken a look at a...

Hi! Managed to install this using python 3.6 and tensorflow 1.13.1 (make crushed with tensorflow-gpu so I deactivated the gpu). Running "python apex.py --env video_pinball --num-timesteps 1000000000 --logdir=/tmp/agent" crashes after...

Rendering an image with brax.io.image

4

I have seen this functionality mentioned in other issues, but I cannot find code that works. Here is my code that attempts to get an image of the environment at...

Sensors in MuJoCo XLA?

3

I see in the documentation of MuJoCO XLA (https://mujoco.readthedocs.io/en/stable/mjx.html) that sensors are under development, any chance this feature has been added? If so, are there any examples?

Check_install fails for Mac

1

I am following the installation instructions for Mac and command `python -m avalon.common.check_install` gives the following output/error: ``` 2023-09-18 16:05:41.149 | INFO | __main__:install_available_binaries_for_current_platform:130 - Installing editor build from https://github.com/Avalon-Benchmark/godot/releases/download...

Are the environments ever reset for DQN?

1

Hi! First I'd like to give my congrats for this project, I find the implementation of DQNs very clean. Looking around I see something that could be a bug: the...

I am trying to run this simple code: ``` from brax import envs env_name = 'ant' backend = 'mjx' env = envs.get_environment(env_name=env_name, backend=backend) print(env.observation_size) print(env.action_size) state = jax.jit(env.reset)(rng=jax.random.PRNGKey(seed=0)) ``` which...