domains / families / media / cosmos-policy

cosmos-policy

separate

Evaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.

When to use

• Evaluating NVIDIA Cosmos Policy on LIBERO or RoboCasa benchmarks
• Profiling inference latency and throughput for Cosmos Policy
• Setting up headless EGL rendering for robot simulation on GPU clusters
• Training or fine-tuning Cosmos Policy from scratch (use official Cosmos training docs)
• Working with OpenVLA-based policies (use `fine-tuning-openvla-oft`)
• Working with Physical Intelligence pi0 models (use `fine-tuning-serving-openpi`)
• Running real-robot evaluation rather than simulation

When not to use

• Training or fine-tuning Cosmos Policy from scratch
• Working with OpenVLA-based policies
• Working with Physical Intelligence pi0 models
• Running real-robot evaluation rather than simulation

Skill page

Source