Sciweavers

76 search results - page 1 / 16
» Reinforcement Learning Based Neural Controllers for Dynamic ...
Sort
View
ICANN
2010
Springer
13 years 6 months ago
Reinforcement Learning Based Neural Controllers for Dynamic Processes without Exploration
Abstract. In this paper we present a Reinforcement Learning (RL) approach with the capability to train neural adaptive controllers for complex control problems without expensive on...
Frank-Florian Steege, André Hartmann, Erik ...
EVOW
2003
Springer
13 years 10 months ago
Exploring the T-Maze: Evolving Learning-Like Robot Behaviors Using CTRNNs
Abstract. This paper explores the capabilities of continuous time recurrent neural networks (CTRNNs) to display reinforcement learning-like abilities on a set of T-Maze and double ...
Jesper Blynel, Dario Floreano
NN
2007
Springer
105views Neural Networks» more  NN 2007»
13 years 4 months ago
Guiding exploration by pre-existing knowledge without modifying reward
Reinforcement learning is based on exploration of the environment and receiving reward that indicates which actions taken by the agent are good and which ones are bad. In many app...
Kary Främling
ICES
2003
Springer
125views Hardware» more  ICES 2003»
13 years 10 months ago
Evolving Reinforcement Learning-Like Abilities for Robots
Abstract. In [8] Yamauchi and Beer explored the abilities of continuous time recurrent neural networks (CTRNNs) to display reinforcementlearning like abilities. The investigated ta...
Jesper Blynel
IJCNN
2006
IEEE
13 years 11 months ago
Reinforcement Learning Control for Biped Robot Walking on Uneven Surfaces
— Biped robots based on the concept of (passive) dynamic walking are far simpler than the traditional fullycontrolled walking robots, while achieving a more natural gait and cons...
Shouyi Wang, Jelmer Braaksma, Robert Babuska, Daan...