LightwheelAI/LW-BenchHubPython
LW-BenchHub is a unified benchmark hub built on Isaac Lab–Arena for embodied AI, providing consistent interfaces, realistic environments, multi-robot support, and large-scale evaluation. It includes Lightwheel-Libero-Tasks and Lightwheel-RoboCasa-Tasks with 268 tasks, reproducible RL configs, and a full pipeline for benchmarking robot policies.
(163 stars) (18 forks) (0 個已索引 issue) (0 個開放 good first issue)