Heuristic Q-Learning Soccer Players: A New Reinforcement Learning Approach to RoboCup Simulation.
Luiz A. CelibertoJackson Paul MatsuuraReinaldo A. C. BianchiPublished in: EPIA Workshops (2007)
Keyphrases
- robocup soccer
- reinforcement learning
- multi agent
- soccer game
- real robot
- robot soccer
- function approximation
- action selection
- soccer games
- reinforcement learning algorithms
- state space
- dynamic programming
- robotic soccer
- model free
- machine learning
- world cup
- temporal difference
- reinforcement learning methods
- temporal difference learning
- continuous state and action spaces
- optimal control
- markov decision processes
- game theory
- optimal policy
- continuous state
- mobile robot
- learning process
- multi agent systems
- cooperative
- learning algorithm
- reward function
- stochastic approximation
- policy evaluation
- multi agent reinforcement learning
- optimal solution