Countering Poisonous Inputs with Memetic Neuroevolution
نویسندگان
چکیده
Applied to certain problems, neuroevolution frequently gets stuck in local optima with very low fitness; in particular, this is true for some reinforcement learning problems where the input to the controller is a high-dimensional and/or ill-chosen state description. Evidently, some controller inputs are “poisonous”, and their inclusion induce such local optima. Previously, we proposed the memetic climber, which evolves neural network topology and weights at different timescales, as a solution to this problem. In this paper, we further explore the memetic climber, and introduce its population-based counterpart: the memetic ES. We also explore which types of inputs are poisonous for two different reinforcement learning problems.
منابع مشابه
A Hypercube-Based Indirect Encoding for Evolving Large-Scale Neural Networks
Research in neuroevolution, i.e. evolving artificial neural networks (ANNs) through evolutionary algorithms, is inspired by the evolution of biological brains. Because natural evolution discovered intelligent brains with billions of neurons and trillions of connections, perhaps neuroevolution can do the same. Yet while neuroevolution has produced successful results in a variety of domains, the ...
متن کاملNeural agents can evolve to reproduce sequences of arbitrary length
We demonstrate that neural agents can evolve behavioral sequences of arbitrary length. In our framework, agents in a two-dimensional arena have to find the secure one among two possible patches, and which of them is secure changes over time. Evolution of arbitrarily long behavioral sequences is achieved by extending the neuroevolution method NEAT with two techniques: Only newly evolved network ...
متن کاملEvolving scalable and modular adaptive networks with Developmental Symbolic Encoding
Evolutionary neural networks, or neuroevolution, appear to be a promising way to build versatile adaptive systems, combining evolution and learning. One of the most challenging problems of neuroevolution is finding a scalable and robust genetic representation, which would allow to effectively grow increasingly complex networks for increasingly complex tasks. In this paper we propose a novel dev...
متن کاملScaffolding for Interactively Evolving Novel Drum Tracks for Existing Songs
A major challenge in computer-generated music is to produce music that sounds natural. This paper introduces NEAT Drummer, which takes steps toward natural creativity. NEAT Drummer evolves a kind of artificial neural network called a Compositional Pattern Producing Network (CPPN) with the NeuroEvolution of Augmenting Topologies (NEAT) method to produce drum patterns. An important motivation for...
متن کاملA Frequency-Domain Encoding for Neuroevolution
Neuroevolution has yet to scale up to complex reinforcement learning tasks that require large networks. Networks with many inputs (e.g. raw video) imply a very high dimensional search space if encoded directly. Indirect methods use a more compact genotype representation that is transformed into networks of potentially arbitrary size. In this paper, we present an indirect method where networks a...
متن کامل