Results 1 - 10
of
79
Automatic Feature Selection in Neuroevolution
"... ABSTRACT Feature selection is the process of finding the set of inputs to a machine learning algorithm that will yield the best performance. Developing a way to solve this problem automatically would make current machine learning methods much more useful. Previous efforts to automate feature selecti ..."
Abstract
- Add to MetaCart
the network's inputs, topology, and weights simultaneously, FS-NEAT addresses the feature selection problem without relying on meta-learning or labeled data. Initial experiments in an autonomous car racing simulation demonstrate that FS-NEAT can learn better and faster than regular NEAT. In addition
Automatic Feature Selection in Neuroevolution
"... ABSTRACT Feature selection is the process of finding the set of inputs to a machine learning algorithm that will yield the best performance. Developing a way to solve this problem automatically would make current machine learning methods much more useful. Previous efforts to automate feature selecti ..."
Abstract
- Add to MetaCart
the network's inputs, topology, and weights simultaneously, FS-NEAT addresses the feature selection problem without relying on meta-learning or labeled data. Initial experiments in an autonomous car racing simulation demonstrate that FS-NEAT can learn better and faster than regular NEAT. In addition
ABSTRACT Automatic Feature Selection in Neuroevolution
"... Feature selection is the process of finding the set of inputs to a machine learning algorithm that will yield the best performance. Developing a way to solve this problem automatically would make current machine learning methods much more useful. Previous efforts to automate feature selection rely o ..."
Abstract
- Add to MetaCart
, topology, and weights simultaneously, FS-NEAT addresses the feature selection problem without relying on meta-learning or labeled data. Initial experiments in an autonomous car racing simulation demonstrate that FS-NEAT can learn better and faster than regular NEAT. In addition, the networks it evolves
Evolving Controllers for Simulated Car Racing
, 2005
"... this paper is what sort of information a control mechanism needs in order to proficiently race a car around a track, and how it should be represented. Along the way we will look at whether different input representations and control mechanisms give rise to qualitatively different driving styles, and ..."
Abstract
- Add to MetaCart
this paper is what sort of information a control mechanism needs in order to proficiently race a car around a track, and how it should be represented. Along the way we will look at whether different input representations and control mechanisms give rise to qualitatively different driving styles
Car Simulation Using Reinforcement Learning
"... This project report presents the result of Reinforcement Learning (RL) experiments in a car simulation. Without any knowledge of the tracks in advance, the car can be trained to avoid bumping into the walls by learning from the given rewards. We have built a car simulation system in which the car ca ..."
Abstract
- Add to MetaCart
This project report presents the result of Reinforcement Learning (RL) experiments in a car simulation. Without any knowledge of the tracks in advance, the car can be trained to avoid bumping into the walls by learning from the given rewards. We have built a car simulation system in which the car
A Simulated Autonomous Car
"... This dissertation describes a simulated autonomous car capable of driving on urbanstyle roads. The system is built around TORCS, an open source racing car simulator. Two real-time solutions are implemented; a reactive prototype using a neural network and a more complex deliberative approach using a ..."
Abstract
- Add to MetaCart
This dissertation describes a simulated autonomous car capable of driving on urbanstyle roads. The system is built around TORCS, an open source racing car simulator. Two real-time solutions are implemented; a reactive prototype using a neural network and a more complex deliberative approach using a
Online Evolution of Deep Convolutional Network for Vision-Based Reinforcement Learning
"... Abstract. Dealing with high-dimensional input spaces, like visual in-put, is a challenging task for reinforcement learning (RL). Neuroevolution (NE), used for continuous RL problems, has to either reduce the prob-lem dimensionality by (1) compressing the representation of the neural network controll ..."
Abstract
- Add to MetaCart
feature vectors computed from the images collected by the recurrent neural network (RNN) con-trollers during their evaluation in the environment. These two interleaved evolutionary searches are used to find MPCNN compressors and RNN controllers that drive a race car in the TORCS racing simulator using
IMITATION LEARNING OF CAR DRIVING SKILLS WITH DECISION TREES AND RANDOM FORESTS
"... Machine learning is an appealing and useful approach to creating vehicle control algorithms, both for simulated and real vehicles. One common learning scenario that is often possible to apply is learning by imitation, in which the behavior of an exemplary driver provides training instances for a sup ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
supervised learning algorithm. This article follows this approach in the domain of simulated car racing, using the TORCS simulator. In contrast to most prior work on imitation learning, a symbolic decision tree knowledge representation is adopted, which combines potentially high accuracy with human
Evolving driving controllers using genetic programming
- In: IEEE Symp Computational Intelligence and Games
"... Abstract-Computational gaming requires the automatic generation of virtual opponents for different game levels. We have turned to artificial evolution to automatically generate such game players. In particular, we have used Genetic Programming to automatically evolve computer programs for computer ..."
Abstract
-
Cited by 6 (0 self)
- Add to MetaCart
(proportional controller). The open race car simulator TORCS was used to evaluate the virtual drivers.
Omnidirectional active vision for evolutionary car driving
- InProceedings of the Ninth International Conference on Intelligent Autonomous Systems
, 2006
"... Perception in intelligent systems is closely coupled with action and the actual environment the system is situated in. Embodied robots exploit by means of sensory-motor coordination the environment in simplifying a complex visually guided task, yielding successful robust perceptual behavior. This ac ..."
Abstract
-
Cited by 2 (2 self)
- Add to MetaCart
, yielding neural controllers of a robotic scale car equipped with an omnidirectional camera that is capable of driving two differently shaped circuits at high-speed without going off-road. Successfully evolved individuals show the sophisticated strategies of an artificial retina selecting quickly only
Results 1 - 10
of
79