Learning Team Strategies: Soccer Case Studies

11 years 11 months ago
Learning Team Strategies: Soccer Case Studies
We use simulated soccer to study multiagent learning. Each team's players (agents) share action set and policy, but may behave di erently due to position-dependent inputs. All agents making up a team are rewarded or punished collectively in case of goals. We conduct simulations with varying team sizes, and compare several learning algorithms: TD-Q learning with linear neural networks (TD-Q), Probabilistic Incremental Program Evolution (PIPE), and a PIPE version that learns by coevolution (CO-PIPE). TD-Q is based on learning evaluation functions (EFs) mapping input/action pairs to expected reward. PIPE and CO-PIPE search policy space directly. They use adaptive probability distributions to synthesize programs that calculate action probabilities from current inputs. Our results show that linear TD-Q encounters several di culties in learning appropriate shared EFs. PIPE and CO-PIPE, however, do not depend on EFs and nd good policies faster and more reliably. This suggests that in som...
Rafal Salustowicz, Marco Wiering, Jürgen Schm
Added 22 Dec 2010
Updated 22 Dec 2010
Type Journal
Year 1998
Where ML
Authors Rafal Salustowicz, Marco Wiering, Jürgen Schmidhuber
Comments (0)