· Contributors · Organizations ·
An Extensible, Data-oriented Architecture for High-performance, Many-world Simulation
DescriptionTraining agents to learn skills in simulated environments is an increasingly important workload at the intersection of AI and graphics. The Madrona framework allows users to build high-performance simulators for novel tasks by leveraging entity-component-system (ECS) interfaces that map task logic onto parallel GPU execution across thousands of environments.
LocationPetree Hall D
Research & Education