Find us at https://princeton-rl.github.io/
👋
At lab meeting today, Royina challenged us to optimize:
Reward = ball speed – # used papers
🤔 Are 12 students better at building than PPO 🤖?
Check out Raj's arxiv.org/abs/2510.06288
👋
At lab meeting today, Royina challenged us to optimize:
Reward = ball speed – # used papers
🤔 Are 12 students better at building than PPO 🤖?
Check out Raj's arxiv.org/abs/2510.06288