Grafting Fine-Tuning and Reinforcement Learning for Empathetic Emotion Elicitation in Dialog Generation.
Ying ZhuBo WangDongming ZhaoKun HuangZhuoxuan JiangRuifang HeYuexian HouPublished in: ECAI (2023)
Keyphrases
- fine tuning
- reinforcement learning
- viable alternative
- function approximation
- fine tune
- fine tuned
- facial expressions
- emotion recognition
- state space
- optimal policy
- dynamic programming
- natural language
- model free
- transfer learning
- user interface
- optimal control
- mixed initiative
- machine learning
- learning algorithm
- robotic control
- affective computing
- preference elicitation
- temporal difference
- learning classifier systems
- decision problems
- markov decision processes
- virtual environment
- learning process
- face recognition