Genetic algorithms with sharing for multimodal function optimization
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Proceedings of the seventh international conference (1990) on Machine learning
Temporal difference learning and TD-Gammon
Communications of the ACM
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Evolving neural networks through augmenting topologies
Evolutionary Computation
Averaging Efficiently in the Presence of Noise
PPSN V Proceedings of the 5th International Conference on Parallel Problem Solving from Nature
Dynamic Programming
Evolving Soccer Keepaway Players Through Task Decomposition
Machine Learning
Exploration and apprenticeship learning in reinforcement learning
ICML '05 Proceedings of the 22nd international conference on Machine learning
Evolutionary Function Approximation for Reinforcement Learning
The Journal of Machine Learning Research
A comparison between cellular encoding and direct encoding for genetic neural networks
GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Efficient non-linear control through neuroevolution
ECML'06 Proceedings of the 17th European conference on Machine Learning
Genetic programming for generalised helicopter hovering control
EuroGP'12 Proceedings of the 15th European conference on Genetic Programming
Safe exploration of state and action spaces in reinforcement learning
Journal of Artificial Intelligence Research
| Hi-index | 0.00 |
Helicopter hovering is an important challenge problem in the field of reinforcement learning. This paper considers several neuroevolutionary approaches to discovering robust controllers for a generalized version of the problem used in the 2008 Reinforcement Learning Competition, in which wind in the helicopter's environment varies from run to run. We present the simple model-free strategy that won first place in the competition and also describe several more complex model-based approaches. Our empirical results demonstrate that neuroevolution is effective at optimizing the weights of multi-layer perceptrons, that linear regression is faster and more effective than evolution for learning models, and that model-based approaches can outperform the simple model-free strategy, especially if prior knowledge is used to aid model learning.