PPO
- Open Source
TRL: Hugging Face's Transformer Reinforcement Learning Library
The alignment of large language models with human preferences is one of the most important challenges in AI development. TRL (huggingface/trl on...
- Open Source
TinyZero: Reproducing DeepSeek R1-Zero's Reasoning with RL for Under $30
DeepSeek R1-Zero was widely regarded as a breakthrough when it was released in January 2025. The model demonstrated that pure reinforcement learning...