scholarly journals Learned Motion Form of a Two-Dimensional Mobile Robot by Using Reinforcement Learning and Its Learning Method Manipulation(Mechanical Systems)

2009 ◽  
Vol 75 (749) ◽  
pp. 122-131 ◽  
Author(s):  
Youngmi JUNG ◽  
Masashi INOUE ◽  
Masayuki HARA ◽  
Jian HUANG ◽  
Tetsuro YABUTA
Keyword(s):  
Reinforcement Learning ◽  
Mobile Robot ◽  
Mechanical Systems ◽  
Learning Method ◽  
Two Dimensional

scholarly journals 2A1-E17 Two-dimensional Motion Acquisition of a Mobile Robot by Reinforcement Learning Method

2006 ◽  
Vol 2006 (0) ◽  
pp. _2A1-E17_1-_2A1-E17_4
Author(s):  
Masashi INOUE ◽  
Masataka SAO ◽  
Masayuki HARA ◽  
Jian HUANG ◽  
Tetsuro YABUTA
Keyword(s):  
Reinforcement Learning ◽  
Mobile Robot ◽  
Learning Method ◽  
Two Dimensional

scholarly journals TRAINING NEURAL NETWORKS USING REINFORCEMENT LEARNING TO REACTIVE PATH PLANNING

2020 ◽  
pp. 1-9
Author(s):  
Milton Calderón ◽  
Esperanza Camargo Casallas
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reinforcement Learning ◽  
Path Planning ◽  
Mobile Robots ◽  
Research Group ◽  
Network Architectures ◽  
Learning Method ◽  
Two Dimensional ◽  
Final Point

The mobile robots are devices with great boom given the possibilities that their utilities offer, and to a greater extent, those freelancers who do not require an operator to perform their functions. In order to consolidate the autonomy it is necessary to generate a system of planning of ways that allows a viable route and as far as possible optimal. This study develops a reactive two-dimensional path planning method with neural networks trained under the reinforcement learning method. The complexity of the scenario between the initial and final point is due to warning and forbidden obstacle zones, and the experimentation is carried out on different neural network architectures, each one as an agent of the learning-by-reinforcement algorithm, being these DQN and DDQN types. The best results are obtained with the DDQN training, reaching the objective in 89% in the validation episodes, although the DQN method shows to be 15.63% faster in its success cases. This work was carried out within the research group DIGITI of the Universidad Distrital Francisco José de Caldas.

A Plant Control Technology Using Reinforcement Learning Method with Automatic Reward Adjustment

2009 ◽  
Vol 129 (7) ◽  
pp. 1253-1263
Author(s):  
Toru Eguchi ◽  
Takaaki Sekiai ◽  
Akihiro Yamada ◽  
Satoru Shimizu ◽  
Masayuki Fukai
Keyword(s):  
Reinforcement Learning ◽  
Control Technology ◽  
Learning Method ◽  
Plant Control
Sign in / Sign up

Export Citation Format

Share Document