MLP gradient decent available across modelscan be optimized using Reinforcement Learning RLPROMPT: Optimizing Discrete Text Prompts with Reinforcement LearningRLPROMPT: Optimizing Discrete Text Prompts with Reinforcement Learning, EMNLP 2022https://velog.io/@mmodestaa/RLPROMPT-Optimizing-Discrete-Text-Promptswith-Reinforcement-Learning
