-
### Description
I am trying to figure out the proper versions for dependencies of Ray RLLib. I tried reading through the Ray documentation and the Ray source code, but I couldn't find the relevant in…
-
In running the following code in google colab for Stock_NeurIPS2018_SB3.ipynb
env_train, _ = e_train_gym.get_sb_env()
I get the following error. Seems related to gym version.
Gynasium 0.28.1 is…
-
Hi there, I am trying to use DeepQLearning to solve the discrete Blackjack Gymnasium environment (Blackjack-v1), where the Observation Space is a tuple, Tuple(Discrete(32), Discrete(11), Discrete(2)),…
-
Hi，
When I convert the demo data to get the RGB video by https://github.com/haosulab/ManiSkill2-Learn/blob/main/scripts/example_demo_conversion/general_rigid_body_single_object_envs.sh . Some tasks…
-
Pyglet supports offscreen rendering through EGL, but PyGame does not.
The combination of RenderFramework.PYGAME and RenderMode.HEADLESS thus currently not work.
For the future, we should fallback …
-
With the movement from `gym` to `gymnasium` the step function also returns a `truncated` flag. This is now always set to `False`, but should be set to something relevant.
-
### What happened + What you expected to happen
Training TD3/DDPG doesn't seem to respect the action bounds, specifically the lower action bound. Specifically, it seems like the action outputs are …
vymao updated
1 month ago
-
Hi @JacopoPan
Thank you for your dedication to maintaining this project. I have noticed several issues with the master branch that seem to limit its functionality.
Could we consider transitioning…
-
This package requires `gym==0.23.1`, influencing which third-party RL libraries are compatible.
Is there potential support for the latest `gym` version v0.26, or even better, the new [`gymnasium`](…
-
The latest Gym API expects `terminated`, `truncated` rather than just `done` after a `env.step()`, and seeds the environment with `env.reset(seed=seed)` rather than `env.seed(seed=seed)`. It is possib…