Updates mimic doc for manipulator success stats

[michaellin6]

Description

Updates mimic doc for manipulator expected success stats for both state-based and visuomotor policy training.
Enhances documentation for SkillGen & Imitation learning workflows.

Type of change

• Documentation update

Checklist

• I have read and understood the contribution guidelines
• I have run the pre-commit checks with ./isaaclab.sh --format
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• I have updated the changelog and the corresponding version in the extension's config/extension.toml file
• I have added my name to the CONTRIBUTORS.md or my name already exists there

[greptile-apps]

Greptile Overview

Greptile Summary

This PR adds a performance benchmarking note to the Franka Cube Stack imitation learning documentation. The addition provides expected metrics for both state-based and visuomotor policy training workflows, including data generation success rates (~50%), training times (30 mins to 6 hours depending on approach), required epochs (600-1000), and expected policy success rates (40-60%). This documentation enhancement follows the existing pattern established for other tasks in the same file (GR-1 pick and place, locomanipulation, and visuomotor nut pour), helping users validate their implementations and set realistic expectations when following the imitation learning tutorial.

Important Files Changed

Filename	Score	Overview
docs/source/overview/imitation-learning/teleop_imitation.rst	5/5	Added performance benchmark note for Franka Cube Stack task with expected success rates and timing information

Confidence score: 5/5

• This PR is safe to merge with minimal risk
• The change is purely additive documentation with no code modifications, adds valuable benchmark information consistent with existing documentation patterns, and addresses a specific documentation gap identified in the linked bug report
• No files require special attention

Sequence Diagram

sequenceDiagram
    participant User
    participant Documentation
    participant PreCommit as Pre-commit Checks
    participant Review as Review Process
    
    User->>Documentation: Update mimic doc for manipulator<br/>success stats
    Note over Documentation: Add expected success rates<br/>and timings for Franka task
    Note over Documentation: Add expected success rates<br/>for GR1T2 pick and place
    Note over Documentation: Add expected success rates<br/>for G1 locomanipulation
    Note over Documentation: Add expected success rates<br/>for GR1T2 nut pouring task
    
    User->>PreCommit: Run ./isaaclab.sh --format
    PreCommit-->>User: Checks passed
    
    User->>Documentation: Verify changes generate<br/>no new warnings
    Documentation-->>User: No warnings generated
    
    User->>Review: Submit PR for release/2.3.0
    Note over Review: PR Type: Documentation update
    Note over Review: Fixes: Enhanced documentation<br/>for SkillGen & Imitation learning
    Review-->>User: Ready for merge

Loading

_{1 file reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}

[greptile-apps]

Greptile Overview

Greptile Summary

This PR adds a documentation note block to the teleoperation and imitation learning guide, providing performance benchmarks for the Franka cube stacking task. The addition aligns with existing documentation patterns used for humanoid robot tasks (GR1T2 pick and place, locomanipulation, and nut pouring) and gives users concrete expectations for both state-based and visuomotor policy training workflows. The note documents data generation success rates (~50%), training times (30 minutes for state-based, 4-6 hours for visuomotor), training epochs (1000 for state, 600 for visuomotor), and final policy success rates (40-60%). This enhancement helps users understand whether their results are within expected ranges when working with the IsaacLab Mimic imitation learning framework.

Important Files Changed

Filename	Score	Overview
docs/source/overview/imitation-learning/teleop_imitation.rst	5/5	Adds performance benchmarks and timing expectations for Franka cube stacking task

Confidence score: 5/5

• This PR is safe to merge with minimal risk and provides valuable documentation improvements
• Score reflects a purely additive documentation change with no code modifications, consistent formatting with existing patterns, and clear value to users
• No files require special attention; the single changed file is straightforward documentation

_{1 file reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}