PMCNS

Novelty search is an evolutionary approach in which the population is driven towards behavioural innovation instead of towards a fixed objective. The use of behavioural novelty to score candidate solutions precludes convergence to local optima. However, in novelty search, significant effort may be spent on exploration of novel, but unfit behaviours. We propose progressive minimal criteria novelty search (PMCNS) to overcome this issue. In PMCNS, novelty search can freely explore the behaviour space as long as the solutions meet a progressively stricter fitness criterion. We evaluate the performance of our approach by evolving neurocontrollers for swarms of robots in two distinct tasks. Our results show that PMCNS outperforms fitness-based evolution and pure novelty search, and that PMCNS is superior to linear scalarisation of novelty and fitness scores. An analysis of behaviour space exploration shows that the benefits of novelty search are conserved in PMCNS despite the evolutionary pressure towards progressively fitter behaviours.

Download Full-text

Novelty Search for Soft Robotic Space Exploration

Proceedings of the 2015 on Genetic and Evolutionary Computation Conference - GECCO '15 ◽

10.1145/2739480.2754731 ◽

2015 ◽

Cited By ~ 11

Author(s):

Georgios Methenitis ◽

Daniel Hennes ◽

Dario Izzo ◽

Arnoud Visser

Keyword(s):

Space Exploration ◽

Novelty Search ◽

Robotic Space Exploration

Download Full-text

Understanding Innovation Engines: Automated Creativity and Improved Stochastic Optimization via Deep Learning

Evolutionary Computation ◽

10.1162/evco_a_00189 ◽

2016 ◽

Vol 24 (3) ◽

pp. 545-572 ◽

Cited By ~ 17

Author(s):

A. Nguyen ◽

J. Yosinski ◽

J. Clune

Keyword(s):

Stochastic Optimization ◽

Distance Function ◽

High Dimensional ◽

Local Optima ◽

Intelligent Software ◽

Novelty Search ◽

Abstract Level ◽

Stochastic Optimization Algorithms ◽

Initial Results

The Achilles Heel of stochastic optimization algorithms is getting trapped on local optima. Novelty Search mitigates this problem by encouraging exploration in all interesting directions by replacing the performance objective with a reward for novel behaviors. This reward for novel behaviors has traditionally required a human-crafted, behavioral distance function. While Novelty Search is a major conceptual breakthrough and outperforms traditional stochastic optimization on certain problems, it is not clear how to apply it to challenging, high-dimensional problems where specifying a useful behavioral distance function is difficult. For example, in the space of images, how do you encourage novelty to produce hawks and heroes instead of endless pixel static? Here we propose a new algorithm, the Innovation Engine, that builds on Novelty Search by replacing the human-crafted behavioral distance with a Deep Neural Network (DNN) that can recognize interesting differences between phenotypes. The key insight is that DNNs can recognize similarities and differences between phenotypes at an abstract level, wherein novelty means interesting novelty. For example, a DNN-based novelty search in the image space does not explore in the low-level pixel space, but instead creates a pressure to create new types of images (e.g., churches, mosques, obelisks, etc.). Here, we describe the long-term vision for the Innovation Engine algorithm, which involves many technical challenges that remain to be solved. We then implement a simplified version of the algorithm that enables us to explore some of the algorithm’s key motivations. Our initial results, in the domain of images, suggest that Innovation Engines could ultimately automate the production of endless streams of interesting solutions in any domain: for example, producing intelligent software, robot controllers, optimized physical components, and art.

Download Full-text

Cognitive gadgets: A provocative but flawed manifesto

Behavioral and Brain Sciences ◽

10.1017/s0140525x19001134 ◽

2019 ◽

Vol 42 ◽

Cited By ~ 2

Author(s):

Marco Del Giudice

Keyword(s):

Theory Of Mind ◽

Cultural Differences ◽

Twin Studies ◽

Cross Cultural ◽

Evolutionary Approach ◽

Genetic Inheritance ◽

Double Standards ◽

Cross Cultural Differences ◽

Cherry Picking ◽

Dichotomous Thinking

Abstract The argument against innatism at the heart of Cognitive Gadgets is provocative but premature, and is vitiated by dichotomous thinking, interpretive double standards, and evidence cherry-picking. I illustrate my criticism by addressing the heritability of imitation and mindreading, the relevance of twin studies, and the meaning of cross-cultural differences in theory of mind development. Reaching an integrative understanding of genetic inheritance, plasticity, and learning is a formidable task that demands a more nuanced evolutionary approach.

Download Full-text