Training Agent for First-Person Shooter Game with Actor-Critic Curriculum Learning.
Yuxin WuYuandong TianPublished in: ICLR (Poster) (2017)
Keyphrases
- reinforcement learning
- learning process
- serious games
- supervised learning
- learning tasks
- actor critic
- active learning
- neural network
- function approximation
- learning algorithm
- computer games
- video games
- multi agent
- learning capabilities
- partially observable
- multi agent systems
- optimal solution
- game playing
- action selection