Multi-population competitive co-evolution of car racing controllers
Authors:
- 1 September 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 1089778X,p. 4043-4050
Abstract
Multi-population competitive co-evolution is explored as a way of developing controllers for a simple (but definitely not trivial) car racing game. The three main uses we see for this method are to evolve more complex general intelligence than would be possible with other methods, to compare different evolvable architectures for controllers, and to develop behaviourally diverse populations of agents for computer games. Nine-population co-evolution is compared with single-population co-evolution and standard evolution strategies, steady-state and generational versions of the algorithm are compared, and a number of different controller architectures are compared with each other.Keywords
This publication has 9 references indexed in Scilit:
- Nonlinear dynamics modelling for controller evolution2007
- Towards automatic personalised content creation for racing games2007
- The Evolution of Multi-Layer Neural Networks for the Control of Xpilot Agents2007
- The N-Strikes-Out Algorithm: A Steady-State Algorithm for Coevolution2006
- Evolving robust and specialized car racing skills2006
- Evolving Controllers for Simulated Car Racing2005
- New Methods for Competitive CoevolutionEvolutionary Computation, 1997
- Finding structure in timeCognitive Science, 1990
- When is it Coevolution?Evolution, 1980