Quantifying the role of complexity in a system’s performance
In this work we studied the relationship between a system’s complexity and its performances in solving a given task. Although complexity is generally assumed to play a key role in an agent’s performance, its influence has not been deeply investigated in the past. To this aim we analysed a predator–prey scenario where a prey had to develop several strategies to counter an increasingly skilled predator. The predator has several advantages over the prey, thus requiring the prey to develop more and more complex strategies. The prey is driven by a fully recurrent neural network trained using genetic algorithms.We conducted several experiments measuring the prey’s complexity using Kolmogorov algorithmic complexity. Our finding is that, in accordance to what was believed in literature, complexity is indeed necessary to solve non-trivial tasks. The main contribution of this work lies in having proved the necessity of complexity to solve non-trivial tasks. This has been made possible by blending together a goal oriented system with a complex one. An experiment is provided to distinguish between the complexity of a chaotic system and the complexity of a random one.
KeywordsComplexity Genetic algorithms Neural networks Chaotic systems
Dr. Riano is supported by InvestNI and the Northern Ireland Integrated Development Fund under the Centre of Excellence in Intelligent Systems project.
- Ashby W (1956) An introduction to cybernetics. University paperbacks. Wiley, New YorkGoogle Scholar
- Bongard J (2008) Behavior chaining: incremental behavior integration for evolutionary robotics. Artif Life 11:64Google Scholar
- Falcioni M, Loreto V, Vulpiani A (2003) Kolmogorov’s legacy about entropy, chaos, and complexity. In: The Kolmogorov legacy in physics, pp 85–108Google Scholar
- Kuusela T, Jartti T, Tahvanainen K, Kaila T (2002) Nonlinear methods of biosignal analysis in assessing terbutaline-induced heart rate and blood pressure changes. Am J Physiol-Heart Circ Physiol 282(2):H773Google Scholar
- Riano L, McGinnity TM (2010) On the emergence of novel behaviours from complex non linear systems. In: Proceeding of BICA 2010. International conference on biological inspired cognitive architectures. IOS PressGoogle Scholar
- Stanley KO, Miikkulainen R (2004) Competitive coevolution through evolutionary complexification. J Artif Intell Res 21(1):63–100Google Scholar
- Werbos P (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550–1560Google Scholar