AI Development
LlamaGym
LlamaGym simplifies the fine-tuning of LLM agents with online reinforcement learning, providing a framework to iterate and experiment across Gym envir
Author: community
What was done
LlamaGym simplifies the fine-tuning of LLM agents with online reinforcement learning, providing a framework to iterate and experiment across Gym environments for efficient agent prompting and hyperparameter tuning
Stack
Llama