Concurrent Hierarchical Reinforcement Learning for RoboCup Keepaway.
Aijun BaiStuart J. RussellXiaoping ChenPublished in: RoboCup (2017)
Keyphrases
- hierarchical reinforcement learning
- robocup soccer
- reinforcement learning
- multi agent
- temporal difference
- model free
- state abstraction
- robotic soccer
- state space
- search algorithm
- function approximation
- reinforcement learning algorithms
- supervised learning
- markov decision processes
- humanoid robot
- reward function
- medium size
- machine learning