Reinforcement learning for the soccer dribbling task.
Arthur CarvalhoRenato OliveiraPublished in: CIG (2011)
Keyphrases
- reinforcement learning
- robocup soccer
- function approximation
- markov decision processes
- state space
- optimal control
- event detection
- learning algorithm
- optimal policy
- multi agent
- robotic control
- dynamic programming
- model free
- temporal difference
- reinforcement learning algorithms
- partially observable
- transfer learning
- neural network
- knowledge base
- robot soccer
- temporal difference learning