1 रिपॉजिटरी
Awesome GitHub RepositoriesInteraction Trajectory Generation
Collecting sequences of agent-environment interactions to build datasets for model fine-tuning.
Distinct from Trajectory-Based Agent Optimization: Focuses on the generation of interaction data for LLM agents, distinct from geometric robotic trajectory generation.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Interaction Trajectory Generation. Refine with filters or upvote what's useful.
Awesome Interaction Trajectory Generation GitHub Repositories
AI के साथ बेहतरीन रिपॉजिटरी खोजें।हम AI का उपयोग करके सबसे सटीक रिपॉजिटरी खोजेंगे।
- openmanus/openmanus-rl
OpenManus/OpenManus-RL
3,916GitHub पर देखेंOpenManus-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
Generates interaction datasets and reasoning paths from environments for model reinforcement learning.
Python
