Reinforcement Learning

Isaac Lab is a modular framework built on NVIDIA Isaac Sim™ that simplifies robot training workflows such as reinforcement and imitation learning. Developers can take advantage of the latest Omniverse™ capabilities for training complex policies with perception enabled.

• Assemble the Scene: The first step is to build a scene in Isaac Sim or Isaac Lab and import robot assets from URDF or MJCF. Apply physics schemas for simulation and integrate sensors for perception-based policy training.
• Define RL Tasks: Once the scene and robot have been configured, the next step is to define the task to be completed and the reward function. The environment (e.g. Manager-Based or Direct Workflow) provides the agent’s current state and observes and executes the actions it provides. The environment then responds to the agents by providing the next states.
• Train: The last step is to define the hyperparameters for training and the policy architecture. Isaac Lab provides four RL libraries for training the models with GPUs—StableBaselines3, RSL-RL, RL-Games, and SKRL.
• Scale: To scale the training across multi-GPU and multi-node systems, developers can use OSMO to orchestrate multi-node training tasks on distributed infrastructure.

NVIDIA Isaac GR00T offers developers a new way to specifically develop humanoid robots. This research initiative and development platform for general-purpose robot foundation models and data pipelines can help understand language, emulate human movements, and rapidly acquire skills through multi-modal learning.

See how our ecosystem is building their own robotics applications and services based on reinforcement learning and NVIDIA technologies.