RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning.
Mingkai DengJianyu WangCheng-Ping HsiehYihan WangHan GuoTianmin ShuMeng SongEric P. XingZhiting HuPublished in: EMNLP (2022)
Keyphrases
- reinforcement learning
- machine learning
- information retrieval
- text retrieval
- keywords
- free text
- multi agent
- natural language generation
- dynamic programming
- text documents
- markov decision processes
- robotic control
- continuous state
- continuous domains
- action selection
- automatically extracted
- database
- mental models
- function approximation
- model free
- information extraction
- multi agent systems
- learning environment
- genetic algorithm
- continuous state and action spaces