Refactor #1
Merged
Refactor #1
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
qgallouedec
reviewed
Apr 6, 2024
qgallouedec
reviewed
Apr 6, 2024
qgallouedec
reviewed
Apr 6, 2024
qgallouedec
reviewed
Apr 7, 2024
| # see https://gymnasium.farama.org/content/migration-guide/#environment-render | ||
| from copy import deepcopy | ||
|
|
||
| model = deepcopy(self.model) |
There was a problem hiding this comment.
Have you tried it? Are the actions applied to self.model forwarded to this copy properly?
There was a problem hiding this comment.
Yes the sizes are set properly, I've checked. I should mention however that sizes are only set when using "rgb_array", but that's because of the way the WindowViewer is set by gym. Also when using "human" because of how the viewer is called the correct "camera0" is not set by default but that's on gym's side, so you have to hit Tab to switch to the correct cam:
 |
 |
qgallouedec
reviewed
Apr 7, 2024
|
LGTM, well done! |
Co-authored-by: Quentin Gallouédec <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This integrates
gymnasium_robotics.envs.robot_env.MujocoRobotEnvintoBasein order for it to not inherit from agymnasium_robotics.GoalEnvand instead simply be agym.Env.It also simplifies a lot of previously entangled code to be much easier to read and comprehend.
Some standard params were added in order to have a similar interface to gym-pusht and aloha:
obs_type: select the observation type to be returned by the step:"state": contains agent and object state vectors only (no rendering)"pixels": contains rendered image only (no state vectors)"pixels_agent_pos": contains rendered image and agent state vectorobservation_width,observation_height: sizes for the observation rendering output byenv.step()(to be fed to the policy)visualization_width,visualization_height: sizes for the visualization rendering, used whenenv.render()is called (for display in eval)env.render()will render for observation by default ("rgb_array"rendering), andenv.render(mode="visualize")will render for visualization.