A Reinforcement Learning-based Offensive semantics Censorship System for Chatbots.
Shaokang CaiDezhi HanZibin ZhengDun LiNoël CrespiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- logic programming
- function approximation
- formal semantics
- temporal difference
- multi agent
- machine learning
- multi agent reinforcement learning
- learning problems
- state space
- learning algorithm
- learning process
- model free
- semantic information
- learning tasks
- evaluation function
- information systems
- optimal control
- default reasoning
- genetic algorithm
- policy gradient
- data mining