Macro action selection with deep reinforcement learning in StarCraft.
Sijia XuHongyu KuangZhi ZhuangRenjie HuYang LiuHuyang SunPublished in: CoRR (2018)
Keyphrases
- action selection
- reinforcement learning
- basal ganglia
- temporal difference
- robot soccer
- function approximation
- continuous state and action spaces
- state space
- model free
- human robot
- decision making
- reinforcement learning algorithms
- markov decision processes
- machine learning
- supervised learning
- dynamic programming
- artificial intelligence
- temporal difference learning
- learning algorithm
- path planning
- optimal control