Results 1 - 10
of
26
Competitive Coevolution through Evolutionary Complexification
- Journal of Artificial Intelligence Research
, 2002
"... 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 demons ..."
Abstract
-
Cited by 202 (71 self)
- Add to MetaCart
(Show Context)
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) method, which evolves increasingly complex neural network architectures. NEAT is applied to an open-ended coevolutionary robot duel domain where robot controllers compete head to head. Because the robot duel domain supports a wide range of sophisticated strategies, and because coevolution benefits from an escalating arms race, it serves as a suitable testbed for observing the effect of evolving increasingly complex controllers. The result is an arms race of increasingly sophisticated strategies. When compared to the evolution of networks with fixed structure, complexifying networks discover significantly more sophisticated strategies. The results suggest that in order to realize the full potential of evolution, and search in general, solutions must be allowed to complexify as well as optimize.
Exploiting open-endedness to solve problems through the search for novelty
- Proceedings of the Eleventh International Conference on Artificial Life (Alife XI
, 2008
"... This paper establishes a link between the challenge of solving highly ambitious problems in machine learning and the goal of reproducing the dynamics of open-ended evolution in artificial life. A major problem with the objective function in machine learning is that through deception it may actually ..."
Abstract
-
Cited by 75 (17 self)
- Add to MetaCart
This paper establishes a link between the challenge of solving highly ambitious problems in machine learning and the goal of reproducing the dynamics of open-ended evolution in artificial life. A major problem with the objective function in machine learning is that through deception it may actually prevent the objective from being reached. In a similar way, selection in evolution may sometimes act to discourage increasing complexity. This paper proposes a single idea that both overcomes the obstacle of deception and suggests a simple new approach to open-ended evolution: Instead of either explicitly seeking an objective or modeling a domain to capture the open-endedness of natural evolution, the idea is to simply search for novelty. Even in an objective-based problem, such novelty search ignores the objective and searches for behavioral novelty. Yet because many points in the search space collapse to the same point in behavior space, it turns out that the search for novelty is computationally feasible. Furthermore, because there are only so many simple behaviors, the search for novelty leads to increasing complexity. In fact, on the way up the ladder of complexity, the search is likely to encounter at least one solution. In this way, by decoupling the idea of open-ended search from only artificial life worlds, the raw search for novelty can be applied to real world problems. Counterintuitively, in the deceptive maze navigation task in this paper, novelty search significantly outperforms objective-based search, suggesting a surprising new approach to machine learning.
A functional self-reproducing cell in a two-dimensional artificial chemistry
- Proceedings of the Ninth International Conference on the Simulation and Synthesis of Living Systems (ALIFE9
, 2004
"... We present a novel unit of evolution: a self-reproducing cell in a two-dimensional artificial chemistry. The cells have a strip of genetic material that is used to produce enzymes, each catalysing a specific reaction that may affect the survival of the cell. The enzymes are kept inside the cell by a ..."
Abstract
-
Cited by 24 (4 self)
- Add to MetaCart
(Show Context)
We present a novel unit of evolution: a self-reproducing cell in a two-dimensional artificial chemistry. The cells have a strip of genetic material that is used to produce enzymes, each catalysing a specific reaction that may affect the survival of the cell. The enzymes are kept inside the cell by a loop of membrane, thus ensuring that only the cell that produced them gets their benefit. A set of reaction rules, each simple and local, allows the cells to copy their genetic information and physically divide. The evolutionary possibilities of the cells are explored, and it is suggested that the system provides a useful framework for testing hypotheses about self-driven evolution.
Passing the alife test: Activity statistics classify evolution in geb as unbounded
- In Proceedings of the European Conference on Artificial Life
, 2001
"... Abstract. Bedau and Packard’s evolutionary activity statistics [1, 2] are used to classify the evolutionary dynamics in Geb [3, 4], a system designed to verify and extend theories behind the generation of evolutionary emergent systems. The result is that, according to these statistics, Geb exhibits ..."
Abstract
-
Cited by 17 (3 self)
- Add to MetaCart
(Show Context)
Abstract. Bedau and Packard’s evolutionary activity statistics [1, 2] are used to classify the evolutionary dynamics in Geb [3, 4], a system designed to verify and extend theories behind the generation of evolutionary emergent systems. The result is that, according to these statistics, Geb exhibits unbounded evolutionary activity, making it the first autonomous artificial system to pass this test. However, having passed it, the most prudent course of action is to look for weaknesses in the test. Two weaknesses are identified and approaches for overcoming them are proposed. 1
Can unrealistic computer models illuminate theoretical biology
- In
, 1999
"... Questions about the important essential properties of biological systems are both di cult to answer and worthwhile to try to answer. Here are three examples of deep open questions in theoretical biology: 1. Is robust multi-level emergent activity anintrinsic property of certain homeostatic self-orga ..."
Abstract
-
Cited by 16 (0 self)
- Add to MetaCart
Questions about the important essential properties of biological systems are both di cult to answer and worthwhile to try to answer. Here are three examples of deep open questions in theoretical biology: 1. Is robust multi-level emergent activity anintrinsic property of certain homeostatic self-organizing systems like cells or organisms, and if so, how is this possible? 2. Is open-ended adaptive evolution an intrinsic property of certain evolving systems like the biosphere, and if so, how? 3. Is unbounded complexity or diversity growth an intrinsic property of certain evolving systems like the biosphere, and if so, how? These questions concern apparent fundamental properties of living systems|properties which, furthermore, seem to be shared bymany other complex adaptive systems, such as the global economy. It is especially hard to address these questions, largely because they concern the global emergent behavior of overwhelmingly complex systems. One way to pursue answers is with a certain sort of unrealistic computational model. Although this may sound paradoxical, I shall argue that, properly understood, it makes perfect sense. I could not agree more when Levin et al. [10] say that \[i]maginative and e cient computational approaches are essential in dealing with the overwhelming complexity of biological systems " (p. 341). There are at least two quite di erent kinds of computational models of complex biological systems. One strives for maximal delity to the details of particular natural systems, exploiting prodigious computer power to push the envelope on micro-mechanical realism. But I am
Unbounded Evolutionary Dynamics in a System of Agents that Actively Process and Transform their Environment
"... Bedau et al.’s statistical classification system for long-term evolutionary dynamics provides a test for open-ended evolution. Making this test more rigorous, and passing it, are two of the most important open problems for research into systems of agents that actively process and transform their env ..."
Abstract
-
Cited by 13 (1 self)
- Add to MetaCart
(Show Context)
Bedau et al.’s statistical classification system for long-term evolutionary dynamics provides a test for open-ended evolution. Making this test more rigorous, and passing it, are two of the most important open problems for research into systems of agents that actively process and transform their environment. This paper presents a detailed description of the application of this test to ‘Geb’, a system designed to verify and extend theories behind the generation of evolutionarily emergent systems. The result is that, according to these statistics, Geb exhibits unbounded evolutionary dynamics, making it the first autonomous artificial system to pass this test. However, having passed it, the most prudent course of action is to look for weaknesses in the test. The test is criticized, most significantly with regard to its normalization method for artificial systems. Furthermore, this paper presents a modified normalization method, based on component activity normalization, that overcomes these criticisms. The results of the revised test, when applied to Geb, indicate that this system does indeed exhibit open-ended evolution.
Exploring the Dynamics of Adaptation with Evolutionary Activity Plots
"... Abstract Evolutionary activity statistics and their visualization are introduced, and their motivation is explained. Examples of their use are described, and their strengths and limitations are discussed. References to more extensive or general accounts of these techniques ..."
Abstract
-
Cited by 12 (0 self)
- Add to MetaCart
(Show Context)
Abstract Evolutionary activity statistics and their visualization are introduced, and their motivation is explained. Examples of their use are described, and their strengths and limitations are discussed. References to more extensive or general accounts of these techniques
Beyond open-endedness: Quantifying impressiveness
- In Proceedings of the Thirteenth International Conference on Artificial Life (ALIFE XIII
, 2012
"... This paper seeks to illuminate and quantify a feature of natural evolution that correlates to our sense of its intuitive greatness: Natural evolution evolves impressive artifacts. Within artificial life, abstractions aiming to capture what makes natural evolution so powerful often focus on the idea ..."
Abstract
-
Cited by 6 (4 self)
- Add to MetaCart
(Show Context)
This paper seeks to illuminate and quantify a feature of natural evolution that correlates to our sense of its intuitive greatness: Natural evolution evolves impressive artifacts. Within artificial life, abstractions aiming to capture what makes natural evolution so powerful often focus on the idea of openendedness, which relates to boundless diversity, complexity, or adaptation. However, creative systems that have passed tests of open-endedness raise the possibility that openendedness does not always correlate to impressiveness in artificial life simulations. In other words, while natural evolution is both open-ended and demonstrates a drive towards evolving impressive artifacts, it may be a mistake to assume the two properties are always linked. Thus to begin to investigate impressiveness independently in artificial systems, a novel definition is proposed: Impressive artifacts readily exhibit significant design effort. That is, the difficulty of creating them is easy to recognize. Two heuristics, rarity and re-creation effort, are derived from this definition and applied to the products of an open-ended image evolution system. An important result is that that the heuristics intuitively separate different reward schemes and provide evidence for why each evolved picture is or is not impressive. The conclusion is that impressiveness may help to distinguish open-ended systems and their products, and potentially untangles an aspect of natural evolution’s mystique that is masked by its co-occurrence with open-endedness.
Achieving High-Level Functionality through Complexification
, 2003
"... An appropriate but challenging goal for evolutionary computation (EC) is to evolve systems of biological complexity. However, specifying ..."
Abstract
-
Cited by 6 (2 self)
- Add to MetaCart
(Show Context)
An appropriate but challenging goal for evolutionary computation (EC) is to evolve systems of biological complexity. However, specifying
