Evolutionary reinforcement learning of artificial neural networks
نویسندگان
چکیده
In this article we describe EANT2, Evolutionary Acquisition of Neural Topologies, Version 2, a method that creates neural networks by evolutionary reinforcement learning. The structure of the networks is developed using mutation operators, starting from a minimal structure. Their parameters are optimised using CMA-ES, Covariance Matrix Adaptation Evolution Strategy, a derandomised variant of evolution strategies. EANT2 can create neural networks that are very specialised; they achieve a very good performance while being relatively small. This can be seen in experiments where our method competes with a different one, called NEAT, NeuroEvolution of Augmenting Topologies, to create networks that control a robot in a visual servoing scenario.
منابع مشابه
Reinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملReinforcement Learning in Neural Networks: A Survey
In recent years, researches on reinforcement learning (RL) have focused on bridging the gap between adaptive optimal control and bio-inspired learning techniques. Neural network reinforcement learning (NNRL) is among the most popular algorithms in the RL framework. The advantage of using neural networks enables the RL to search for optimal policies more efficiently in several real-life applicat...
متن کاملDeep learning in neural networks: An overview
In recent years, deep artificial neural networks (including recurrent ones) have won numerous contests in pattern recognition and machine learning. This historical survey compactly summarizes relevant work, much of it from the previous millennium. Shallow and Deep Learners are distinguished by the depth of their credit assignment paths, which are chains of possibly learnable, causal links betwe...
متن کاملFitness Value Optimization for Disc Set in Board Game through Evolutionary Learning
The Artificial Intelligence research field since ages has incorporated a series of novel and trend setting distinct approaches including neural networks, fuzzy logic and genetic algorithms to apply them to various problem-solving domains. Machine learning techniques such as evolutionary learning, neural networks and reinforcement learning alone are difficult to apply to board games because they...
متن کاملLearning Algorithms for Small Mobile Robots: Case Study on Maze Exploration
An emergence of intelligent behavior within a simple robotic agent is studied in this paper. Two control mechanisms for an agent are considered — new direction of reinforcement learning called relational reinforcement learning, and a radial basis function neural network trained by evolutionary algorithm. Relational reinforcement learning is a new interdisciplinary approach combining logical pro...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Int. J. Hybrid Intell. Syst.
دوره 4 شماره
صفحات -
تاریخ انتشار 2007