Repository Index

Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

• llama
• llm
• pretraining
• agent

An elegant PyTorch deep reinforcement learning library.

• pytorch
• policy-gradient
• dqn
• double-dqn

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

• rl
• ml
• ai
• google

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

• llms
• lora
• reinforcement-learning
• agent

A curated list of Monte Carlo tree search papers with implementations.

• tree-search
• learning
• machine-learning
• deep-learning