Skip to content

Feature/turtle2 generic deploy env#1152

Draft
MuggleZzzH wants to merge 29 commits into
RLinf:mainfrom
MuggleZzzH:feature/turtle2-generic-deploy-env
Draft

Feature/turtle2 generic deploy env#1152
MuggleZzzH wants to merge 29 commits into
RLinf:mainfrom
MuggleZzzH:feature/turtle2-generic-deploy-env

Conversation

@MuggleZzzH

Copy link
Copy Markdown
Contributor

Description

Motivation and Context

How has this been tested?

Additional information (optional, e.g., figures and logs):

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Documentation update (Document-only update)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)

Checklist:

  • My code follows the code style of this project.
  • My change requires a change to the documentation.
  • I have updated the documentation accordingly.
  • I have added tests to cover my changes.
  • All new and existing tests passed.

MuggleZzzH and others added 29 commits May 6, 2026 02:39
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
relative_pose mode now applies DualRelativeFrame by default
(use_relative_frame=True), matching the training wrapper contract where
policy actions are in EE frame and observations are relative to reset pose.
Use use_relative_frame=False to opt out.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Signed-off-by: MuggleZzzH <2558818257@qq.com>
Aligns apply_dual_pose_action_wrappers with the single-arm and dual-arm
builders so that human reward labelling (KeyboardRewardDoneWrapper /
KeyboardRewardDoneMultiStageWrapper) can be enabled via
keyboard_reward_wrapper config. Defaults to None (disabled).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: MuggleZzzH <2558818257@qq.com>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Signed-off-by: Codex PR1082 Repro <codex-pr1082-repro@example.local>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants