Keyboard shortcuts

Press ← or → to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Integration — Reinforcement Learning

SRB’s Gymnasium environments support the RL adapters below. Compatibility varies by framework and task; see the compatibility matrix.

Motivation

Simulation supports RL development and evaluation, but does not establish hardware readiness.

Available Integrations

We provide official integrations with the following RL frameworks:

  • Dreamer [JAX] - Model-based RL algorithm
  • Stable-Baselines3 (SB3) & SBX [PyTorch & JAX] - Popular implementation of RL algorithms
  • skrl [PyTorch] - Supports the adapter’s pinned API version; check the installed SRB profile for compatibility.
  • TD-MPC2 [PyTorch] - Scalable model-based RL with strong sample efficiency
  • RSL-RL [PyTorch] - Fast on-policy algorithms (PPO) used widely in legged locomotion research

SKRL AMP and other profile-specific providers may be gated. See the capability ledger for evidence status and agent configuration for supported options.

How to Get Started?

See Installation, Basic Usage, and the RL Workflow.