Several researchers have demonstrated how complex behavior can be learned through neuro-evolution (i.e. evolving neural networks with genetic algorithms). However, complex general behavior such as evading predators or avoiding obstacles, which is not tied to specific environments, turns out to be very difficult to evolve. Often the system discovers mechanical strategies (such as moving back and forth) that help the agent cope, but are not very effective, do not appear believable and would not generalize to new environments. The problem is that a general strategy is too difficult for the evolution system to discover directly. This paper proposes an approach where such complex general behavior is learned incrementally, by starting with simpler behavior and gradually making the task more challenging and general. The task transitions are implemented through successive stages of delta-coding (i.e. evolving modifications), which allows even converged populations to adapt to the new task. The method is tested in the stochastic, dynamic task of enemy avoidance, and compared with direct evolution. The incremental approach evolves more effective and more general behavior, and should also scale up to harder tasks.

PDF, PS

Adaptive Behavior(5):317-342, 1997.

@Article{gomez:ab97, title={Incremental Evolution Of Complex General Behavior}, author={Faustino Gomez and Risto Miikkulainen}, journal={Adaptive Behavior}, number={5}, pages={317-342}, url="http://nn.cs.utexas.edu/?gomez:ab97", year={1997} }