The Advantage of Doubling: A Deep Reinforcement Learning Approach to Studying the Double Team in the NBA.
Jiaxuan WangIan FoxJonathan SkazaNick LinckSatinder SinghJenna WiensPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- model free
- team members
- optimal control
- learning algorithm
- information retrieval
- dynamic programming
- artificial neural networks
- learning environment
- database
- reinforcement learning algorithms
- deep learning
- virtual teams
- temporal difference learning
- robotic soccer
- robocup soccer