RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning.
Mingkai DengJianyu WangCheng-Ping HsiehYihan WangHan GuoTianmin ShuMeng SongEric P. XingZhiting HuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- information retrieval
- function approximation
- machine learning
- text mining
- text retrieval
- model free
- text documents
- string matching
- free text
- markov decision processes
- document analysis
- natural language generation
- discrete space
- discrete version
- continuous domains
- discrete geometry
- natural language text
- action selection
- neural network
- textual data
- textual information
- finite number
- learning processes
- co occurrence
- state space
- dynamic programming
- keywords
- data mining