Learning to Design Games: Strategic Environments in Deep Reinforcement Learning.
Haifeng ZhangJun WangZhiming ZhouWeinan ZhangYing WenYong YuWenxin LiPublished in: CoRR (2017)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- supervised learning
- learning tasks
- learning agents
- online learning
- state space
- autonomous learning
- case study
- active learning
- multiagent learning
- game theory
- function approximation
- learning games
- temporal difference learning
- multi agent decision making
- board game
- learning capabilities
- action selection
- video games
- machine learning
- markov decision processes
- optimal policy