PecidRL: Petition expectation correction and identification based on deep reinforcement learning.
Ying LiWensi FangHang SunXiangyu LiuWei DuYijun LiuQianqian LiPublished in: Inf. Process. Manag. (2023)
Keyphrases
- reinforcement learning
- multi agent
- function approximation
- learning algorithm
- learning process
- data sets
- identification rate
- deep learning
- markov decision process
- reinforcement learning algorithms
- optimal control
- state space
- artificial intelligence
- evaluation function
- optimal policy
- model free
- multiscale
- neural network
- person identification
- multi agent reinforcement learning
- real time