Implementing Parametric Reinforcement Learning in Robocup Rescue Simulation.
Omid AghazadehMaziar Ahmad SharbafiAbolfazl Toroghi HaghighatPublished in: RoboCup (2007)
Keyphrases
- robocup rescue
- reinforcement learning
- multi agent
- model free
- temporal difference
- learning problems
- international competition
- real robot
- function approximation
- markov decision processes
- mathematical model
- neural network
- optimal control
- optimal policy
- state space
- simulation environment
- simulation models
- learning process
- robotic control
- learning algorithm
- machine learning