Reinforcement Learning of Robotic Motion with Genetic Programming, Simulated Annealing and Self-Organizing Map

Created by W.Langdon from gp-bibliography.bib Revision:1.7662

@InProceedings{Wing-KwongWong:2011:TAAI,

• author = "Wing-Kwong Wong and Hsin-Yu Chen and Chung-You Hsu and Tsung-Kai Chao",
• title = "Reinforcement Learning of Robotic Motion with Genetic Programming, Simulated Annealing and Self-Organizing Map",
• booktitle = "International Conference on Technologies and Applications of Artificial Intelligence (TAAI 2011)",
• year = "2011",
• month = "11-13 " # nov,
• pages = "292--298",
• publisher = "IEEE",
• address = "Chung-Li, Taiwan",
• keywords = "genetic algorithms, genetic programming, PSG, Player/Stage/Gazebo, Q-learning, Q-table, SOM, machine learning, optimal action, reinforcement learning, robotic motion, self-organising map, simulated annealing, control engineering computing, learning (artificial intelligence), robots, self-organising feature maps, simulated annealing",
• isbn13 = "978-1-4577-2174-8",
• DOI = "doi:10.1109/TAAI.2011.57",
• size = "7 pages",
• abstract = "Reinforcement learning, a sub-area of machine learning, is a method of actively exploring feasible tactics and exploiting already known reward experiences in order to acquire a near-optimal policy. The Q-table of all state-action pairs forms the basis of policy of taking optimal action at each state. But an enormous amount of learning time is required for building the Q-table of considerable size. Moreover, Q-learning can only be applied to problems with discrete state and action spaces. This study proposes a method of genetic programming with simulated annealing to acquire a fairly good program for an agent as a basis for further improvement that adapts to the constraints of an environment. We also propose an implementation of Q-learning to solve problems with continuous state and action spaces using Self-Organising Map (SOM). An experiment was done by simulating a robotic task with the Player/Stage/Gazebo (PSG) simulator. Experimental results showed the proposed approaches were both effective and efficient.",
• notes = "Also known as \cite{6120760}",

}

Genetic Programming entries for Wing-Kwong Wong Hsin-Yu Chen Chung-You Hsu Tsung-Kai Chao

Citations