dm_env icon indicating copy to clipboard operation
dm_env copied to clipboard

A Python interface for reinforcement learning environments

Results 6 dm_env issues
Sort by recently updated
recently updated
newest added

Bumps [numpy](https://github.com/numpy/numpy) from 1.21.4 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...

dependencies

Hi! I was looking at environments used in dm_control but I couldn't figure out how to render the environment inherited from dm_env. Is there a function like the render function...

Was wondering if I could reset an environment to a particular state and instead of calling env.step to get a timestep and observation, I could call a function to get...

Would be useful to have a `sample()` function for the specs, like in [gym spaces](https://github.com/Farama-Foundation/Gymnasium/blob/3fda2072d6c1e76e76127eabb080862b7afa6e9a/gymnasium/spaces/space.py#L92). I can raise a PR if this is fine by you guys.

Hi, I was wondering if there were plans to by default support `tree` like structures in dm_env.specs. This would be extremely relevant to jax-based environments, or generic environments utilizing `deepmind/tree`,...

Wondering why the return of `def generate_value()` in `BoundedArray(Array)` is multiplied by the `self.minimum` rather then a random number e.g. Is this intended behavior? I guess it's still a valid...