Sciweavers

Share
AROBOTS
1999

Reinforcement Learning Soccer Teams with Incomplete World Models

11 years 8 months ago
Reinforcement Learning Soccer Teams with Incomplete World Models
We use reinforcement learning (RL) to compute strategies for multiagent soccer teams. RL may pro t signi cantly from world models (WMs) estimating state transition probabilities and rewards. In high-dimensional, continuous input spaces, however, learning accurate WMs is intractable. Here we show that incomplete WMs can help to quickly nd good action selection policies. Our approach is based on a novel combination of CMACs and prioritized sweeping-like algorithms. Variants thereof outperform both Q( )-learning with CMACs and the evolutionary method Probabilistic Incremental Program Evolution (PIPE) which performed best in previous comparisons.
Marco Wiering, Rafal Salustowicz, Jürgen Schm
Added 22 Dec 2010
Updated 22 Dec 2010
Type Journal
Year 1999
Where AROBOTS
Authors Marco Wiering, Rafal Salustowicz, Jürgen Schmidhuber
Comments (0)
books