Multitask Policy Adversarial Learning for Human-Level Control With Large State Spaces.
Junping WangYoukang ShiWensheng ZhangIan ThomasShihui DuanPublished in: IEEE Trans. Ind. Informatics (2019)
Keyphrases
- multi task
- learning tasks
- multitask learning
- learning algorithm
- multi task learning
- learning process
- human level
- learning problems
- reinforcement learning
- state space
- multiple tasks
- artificial general intelligence
- supervised learning
- control system
- active learning
- artificial neural networks
- support vector
- machine intelligence
- data mining