RL

Posts about reinforcement learning.

• Introduction to Policy Gradient for LMs (09 Feb 2026) technical rl nlp
  

  A basic introduction to policy gradient for language models.

• Results Replicating L1 for Tulu (02 Feb 2026) technical rl nlp
  

  Results replicating the recent L1 paper.

• Reinforcement Learning with Pokemon (02 Aug 2021) technical rl games
  

  Looking into using reinforcement learning to train Pokemon battle bots.