Ludo Robotics releases Prompt-to-Policy reinforcement-learning system
Ludo Robotics and KRAFTON AI released an open-source agentic system that turns natural-language behavior requests into trained robot policies.
Evidence notes
- The system writes reward functions, trains policies with PPO and evaluates rollouts using code and vision-language judges.
- Its release includes a web dashboard and support for MuJoCo environments, with optional IsaacLab integration.
- The official technical report demonstrated 64 learned behaviors and published the full training and evaluation repository under an MIT license.
Company context
Ludo Robotics is a physical-AI research company focused on social humanoid intelligence across perception, learning, and human-robot interaction for robots that understand both the physical and social world.