Open
Conversation
…diChain into yueci/add-sim-docs
yuecideng
requested changes
Jan 26, 2026
|
|
||
|
|
||
| @register_env("PushTRL", max_episode_steps=50, override=True) | ||
| class PushTEnv(EmbodiedEnv): |
Contributor
There was a problem hiding this comment.
We should inherit RLEnv for now.
| super()._initialize_episode(env_ids=env_ids, **kwargs) | ||
| # self._draw_goal_marker() | ||
|
|
||
| def _step_action(self, action: EnvAction) -> EnvAction: |
Contributor
There was a problem hiding this comment.
We now have standard preprocess_action function, so _step_action should not be modified.
| self.robot.set_qpos(qpos=target_qpos) | ||
| return scaled_action | ||
|
|
||
| def _get_eef_pos(self) -> torch.Tensor: |
Contributor
There was a problem hiding this comment.
We should implement a standard eef_pose computation method. cc @yhnsu
| def evaluate(self, **kwargs) -> Dict[str, Any]: | ||
| info = self.get_info(**kwargs) | ||
| return { | ||
| "success": info["success"][0].item(), |
Contributor
There was a problem hiding this comment.
success should be a vector?
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR adds a new Reinforcement Learning task environment PushTRL (Push-T).
Changes include:
Environment Implementation: Added
PushTEnvclass which defines the task of pushing a T-shaped block to a goal using a UR10 manipulator. This also provides the relevant parameters for the task.Checklist