FlashREINFORCE: to our knowledge, the first open-source critic-free, single-rollout async LLM RL with 6,000+ stable updates.
One-Batch REINFORCE + Sequence Trust Region + Sample-Mean Optimization.
Paper:
Code:
Show more
1/ Still looking for a minimalist, high-performance framework for agentic RL research?
Meet Molt — an agentic-first, PyTorch-native reinforcement learning framework with roughly 9K lines of RL code for 700B models.
⭐
Show more
