Self-Play and AI Feedback

Self play is where a model interacts with itself to improve - for example self-play against itself to get better at a game.

• AlphaGo: Silver et al 2016 - Mastering The Game of Go with Deep Neural Networks and Tree Search

• Fu et al 2023 - Improving Language Model Negotiation with Self-Play and In-Context Learning from AI Feedback

• GANs
• Human-in-the-Loop
• Reinforcement Learning