AI Trends 2023: Reinforcement Learning - RLHF, Robotic Pre-Training, and Offline RL with Sergey Levine - #612
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
00:00
Inverse RL for Chat Bots
Inverse reinforcement learning is a harder problem than reinforcement learning, because inverse reinforcement requires a mental simulation of what different objectives would lead to./nForward reinforcement learning is possible with language models, and this could be helpful for detecting deceptive or manipulative bots.
Transcript
Play full episode
