Off-Policy General Value Functions to Represent Dynamic Role Assignments in RoboCup 3D Soccer Simulation

1 code implementation • 18 Feb 2014 • Saminda Abeyruwan, Andreas Seekircher, Ubbo Visser

Collecting and maintaining accurate world knowledge in a dynamic, complex, adversarial, and stochastic environment such as the RoboCup 3D Soccer Simulation is a challenging task.

Reinforcement Learning (RL) World Knowledge