1 dépôt
Specific algorithmic recipes used to train models for complex reasoning and agentic behavior.
Distinct from Agentic Reasoning Applications: Focuses on the training recipes and RL implementations for reasoning, rather than the final application of the models.
Explore 1 awesome GitHub repository matching part of an awesome list · Reasoning Recipe Implementations. Refine with filters or upvote what's useful.
RLinf is a distributed reinforcement learning orchestrator and embodied AI training framework. It provides the infrastructure to train vision-language-action models and robotic policies using a combination of reinforcement learning and supervised fine-tuning. The system is designed for scaling workloads across GPU clusters, managing the placement of actors, rollout workers, and environment components. It features a specialized robotics data collection pipeline for gathering teleoperated demonstrations and simulation trajectories into standardized replay buffers, alongside a hardware interface
Implements reinforcement learning recipes to enhance agentic behavior and complex reasoning in large language models.