1 مستودع
Architectures for collecting interaction trajectories by running parallel simulations across worker nodes.
Distinct from Distributed Architectures: Existing distributed architecture tags focus on general software or storage, not RL trajectory collection.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Distributed Rollout Systems. Refine with filters or upvote what's useful.
OpenManus-RL is a reinforcement learning framework and distributed training pipeline designed to train large language models as agents. It serves as an agentic reasoning optimizer and reward model trainer, providing the infrastructure to improve model decision-making through reward-based policy optimization. The project distinguishes itself through a distributed architecture that supports parameter sharding across multiple compute nodes and a coordinated rollout system for collecting interaction trajectories. It incorporates advanced reasoning strategies, such as Tree-of-Thoughts and Monte Ca
Ships a coordinated rollout system that collects interaction trajectories across multiple worker nodes.