Q-Learning in Simulated Robotic Soccer - Large State Spaces and Incomplete Information

Reinforcement Learning in Large State Spaces: Simulated Robotic Soccer as a testbed

Keepaway Soccer: A Machine Learning Testbed

RoboCup simulated soccer presents many challenges to machine learning (ML) methods, including a large state space, hidden and uncertain state, multiple agents, and long and variable delays in the effects of actions. While there have been many successful ML applications to portions of the robotic soccer task, it appears to be still beyond the capabilities of modern machine learning techniques to...

Team Description Paper GPR-2D 2012

 This document describes a simulated robotic soccer team (GPR-2D). The team is implemented using an Artificial Intelligence (AI) strategy to modify the behavior of players of one team of soccer robots of the RoboCup 2D simulation category. This strategy used is a Reinforcement Learning (RL) algorithm, Q-learning. This algorithm define how each agent should act according to the characteristics ...

Learning a Partial Behavior for a Competitive Robotic Soccer Agent

Robotic soccer is a highly competitive domain. Accordingly, the use of learnt behaviors in this application field presumes not only learning algorithms that are known to converge and produce stable results, but also imposes the wish for obtaining optimal or at least near-optimal behaviors, even when working within high-dimensional and continuous state/action spaces. This paper deals with the co...

A Two Pass Learning Algorithm for Simulated Soccer

Reinforcement learning (RL) is an effective machine learning paradigm, but because the state space cardinality often grows exponentially as the dimensionality grows linearly, many domains are not well-suited for traditional RL techniques. Tile coding with linear function approximation has been widely used to circumvent the curse of dimensionality, but suffers from the drawback that trial and er...