Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Genetic Programming and Evolvable Machines
ALPS: the age-layered population structure for reducing the problem of premature convergence
Proceedings of the 8th annual conference on Genetic and evolutionary computation
Restricted gradient-descent algorithm for value-function approximation in reinforcement learning
Artificial Intelligence
Accelerated Neural Evolution through Cooperatively Coevolved Synapses
The Journal of Machine Learning Research
The challenge of irrationality: fractal protein recipes for PI
Proceedings of the 11th Annual conference on Genetic and evolutionary computation
Fractal gene regulatory networks for robust locomotion control of modular robots
SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Fractal gene regulatory networks for control of nonlinear systems
PPSN'10 Proceedings of the 11th international conference on Parallel problem solving from nature: Part II
ReNCoDe: a regulatory network computational device
EuroGP'11 Proceedings of the 14th European conference on Genetic programming
Evolving genes to balance a pole
EuroGP'10 Proceedings of the 13th European conference on Genetic Programming
| Hi-index | 0.00 |
Evolution produces gene regulatory networks (GRNs) able to control cells. With this inspiration we evolve artificial GRN (AGRN) genomes for the reinforcement learning control of mechanical systems with unknown dynamics, a problem domain similar in its sparse feedback to that of controlling a biological cell. From the fractal GRN (FGRN), a successful but complex GRN model, we obtain the Input-Merge-Regulate-Output (IMRO) abstraction for GRN-based controllers, in which the FGRN's complex fractal operations are replaced by simpler ones. Computational experiments on reinforcement learning problems show significant improvements from the use of this simplified approach. We also present the first evolutionary solution to a hardened version of the acrobot problem, which previous evolutionary methods have failed on.