Argumentation-Based Reinforcement Learning for RoboCup Keepaway.
Yang GaoFrancesca ToniRobert CravenPublished in: COMMA (2012)
Keyphrases
- robocup soccer
- reinforcement learning
- temporal difference
- multi agent
- robotic soccer
- function approximation
- learning algorithm
- markov decision processes
- supervised learning
- partially observable
- medium size
- action space
- real robot
- state space
- reinforcement learning algorithms
- genetic algorithm
- formal representation
- model free
- td learning
- robotic control
- dynamic programming