Example Gallery

This section presents the collection of examples currently supported by RLinf, showcasing how the framework can be applied across different scenarios and demonstrating its efficiency in practice. This example gallery is continuously expanding, covering new scenarios and tasks to highlight RLinf’s flexibility and efficiency.

• Embodied Scenarios: Embodied training examples using state-of-the-art (SOTA) models across different benchmarks and real robotic platforms.

• Agentic Scenarios: Agentic training examples covering math reasoning and agentic AI workflows, including both single-agent and multi-agent settings.

• System-level Optimizations: Examples demonstrating flexible and dynamic scheduling of computing resources, as well as assignment to the most suitable hardware devices.