Exposes state_dependent_std parameter in rl_cfg for rsl_rl.

[ashwinvkNV]

Description

Adds a new state_dependent_std param to the rsl_rl_config for IsaacLab.

[greptile-apps]

Greptile Overview

Greptile Summary

Added state_dependent_std boolean parameter to the RslRlPpoActorCriticCfg configuration class with a default value of False.

• Parameter positioned logically alongside other noise-related configuration (init_noise_std, noise_std_type)
• Includes proper docstring documentation
• Default value maintains backward compatibility with existing configurations

Confidence Score: 5/5

• This PR is safe to merge with minimal risk
• Simple configuration parameter addition with proper defaults, documentation, and no breaking changes. The parameter is well-positioned with related noise configuration options and maintains backward compatibility.
• No files require special attention

Important Files Changed

File Analysis

Filename	Score	Overview
source/isaaclab_rl/isaaclab_rl/rsl_rl/rl_cfg.py	5/5	Added state_dependent_std boolean parameter with default False to RslRlPpoActorCriticCfg configuration class

Sequence Diagram

sequenceDiagram
    participant User as User/Task Config
    participant Config as RslRlPpoActorCriticCfg
    participant Runner as OnPolicyRunner
    participant Library as rsl-rl-lib (ActorCritic)
    
    User->>Config: Initialize with state_dependent_std=True/False
    Config->>Config: Set default state_dependent_std=False
    User->>Runner: Create runner with policy config
    Runner->>Library: Pass policy config including state_dependent_std
    Library->>Library: Use state_dependent_std to configure policy network
    Note over Library: If True: std depends on state<br/>If False: std is fixed parameter

Loading

[greptile-apps]

_{1 file reviewed, no comments}

_{Edit Code Review Agent Settings | Greptile}