Heterogeneous complexification strategies robustly outperform homogeneous strategies for incremental evolution

نویسندگان

  • Adam Stanton
  • Alastair Channon
چکیده

The evolution of naturalistic, embodied agents and behaviours has been a long-standing goal of Artificial Life since the initial, impressive work of Karl Sims. Incremental evolution has been used extensively to improve the quality of evolutionary search in many complex, non-linear problem spaces. This work sets out to disambiguate the lexicon around incremental evolution, advocating the term environmental complexification to represent the complexification of the problem domain. We then go on to analyse various complexification strategies in a structured, complexifiable and yet simple environment: a 3D agent-based obstacle task. We divide the strategies conceptually into homogeneous and heterogeneous; homogeneous strategies expose successive generations of the population to a single or tightly clustered range of objective functions while heterogeneous strategies present many, covering the range of complexity. It was found that widely-used homogeneous complexification techniques, for example direct presentation of difficult tasks or linearly-increased difficulty, fail due to either loss-of-gradient or temporally-local over-fitting (analogous to catastrophic forgetting in neural systems). Heterogeneous methods of complexification (including oscillatory strategies) that eliminate these issues are devised and tested. The heterogeneous category outperforms the homogeneous in all metrics, establishing a much more robust approach to the evolution of naturalistic embodied agents.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Competitive Coevolution through Evolutionary Complexification

Two major goals in machine learning are the discovery of complex multidimensional solutions and continual improvement of existing solutions. In this paper, we argue that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals. We demonstrate the power of complexification through the NeuroEvolution of Augmenting Topologies (NEAT) me...

متن کامل

Continual Coevolution Through Complexification

In competitive coevolution, the goal is to establish an “arms race” that will lead to increasingly sophisticated strategies. However, in practice, the process often leads to idiosyncrasies rather than continual improvement. Applying the NEAT method for evolving neural networks to a competitive simulated robot duel domain, we will demonstrate that (1) as evolution progresses the networks become ...

متن کامل

Coevolution of strategies and update rules in the Prisoner's Dilemma game on complex networks

In this work we study a weak Prisoner’s Dilemma game in which both strategies and update rules are subjected to evolutionary pressure. Interactions among agents are specified by complex topologies, and we consider both homogeneous and heterogeneous situations. We consider deterministic and stochastic update rules for the strategies, which in turn may consider single links or full context when s...

متن کامل

Effective Strategies for Optimal Implementation of Evolution and Innovation Packages in Medical Education

ABSTRACT BACKGROUND AND OBJECTIVE: Evolution and innovation packages in medical science education are the main program of medical education and it is necessary to pay attention to the provision of infrastructure of their implementation. This study was conducted to identify effective strategies for optimal implementation of evolution and innovation packages in medical education. METHODS: The met...

متن کامل

Evolution-inspired incremental development of complex autonomous intelligence

This article presents Hypothetical Evolutionary Paths (HEP), an evolutioninspired methodology for incremental development of complex adaptive robot control algorithms. HEP produces algorithms that adapt without learning centralized hypotheses in the same way that behavior-based approaches in general avoid the use of centralized world models. The algorithms produced adapt rapidly without sufferi...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2013