Publications (9)7.28 Total impact
-
Conference Proceeding: An adaptive state aggregation approach to Q-learning with real-valued action function.
Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Istanbul, Turkey, 10-13 October 2010; 01/2010 -
Conference Proceeding: Behavioral-Fusion Control Based on Reinforcement Learning.
Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, San Antonio, TX, USA, 11-14 October 2009; 01/2009 -
Conference Proceeding: Tree-like Function Approximator in Reinforcement Learning
[show abstract] [hide abstract]
ABSTRACT: State value estimating is an important issue in reinforcement learning. It affects the performance significantly. The methods of lookup tables have advantages in convergence rate. But they need prior knowledge about how to partition the state space in advance. It is also not reasonable in a real system since the values associated with different sensory inputs but belonging to a representing state are the same. We proposed a method to discretize the state space adaptively and effectively in terms of an approach akin to decision tree methods. In each (discretized) presenting state, function approximators based on the tree structure estimate the values precisely.Industrial Electronics Society, 2007. IECON 2007. 33rd Annual Conference of the IEEE; 12/2007 -
Article: Reinforcement Learning in Strategy Selection for a Coordinated Multirobot System
[show abstract] [hide abstract]
ABSTRACT: This correspondence presents a multistrategy decision making system for robot soccer games. Through reinforcement processes, the coordination between robots is learned in the course of game. Meanwhile, a better action can be granted after an iterative learning process. The experimental scenario is a five-versus-five soccer game, where the proposed system dynamically assigns each player to a position in a primitive role, such as attacker, goalkeeper, etc. The responsibility of each player varies along with the change of the role in state transitions. Therefore, the system uses several strategies, such as offensive strategy, defensive strategy, and so on, for a variety of scenarios. Thus, the decision-making mechanism can choose a better strategy according to the circumstances encountered. In each strategy, a robot should behave in coordination with its teammates and resolve conflicts aggressively. The major task assignment to robots in each strategy is simply to catch good positions. Therefore, the problem of dispatching robots to good positions in a reasonable manner should be effectively handled with. This kind of problem is similar to assignment problems in linear programming research. Utilizing the Hungarian method, each robot can be assigned to its assigned spot with minimal cost. Consequently, robots based on the proposed decision-making system can accomplish each situational task in coordination.IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans 12/2007; · 2.12 Impact Factor -
Conference Proceeding: Behavior Cloning by a Self-Organizing Decision Tree
[show abstract] [hide abstract]
ABSTRACT: It is hard to define a state space or the proper reward function in reinforcement learning to make the robot act as expected. In this paper, we demonstrate the expected behavior for a robot Then a RL-based decision tree approach which decides to split according to long-term evaluations, instead of a top-down greedy strategy which finds out the relationship between the input and output from the demonstration data. We use this method to teach a robot for target seeking problem. In order to promote the performance in tackling target seeking problem, we add a Q-learning along with the state space based on RL-based decision tree. The experiment result shows that Q-Iearning can promote the performance quickly. For demonstration, we build a mobile robot powered by an embedded board. The robot can detect the hall of the range in any direction with omni-directional vision system. With such powerful embedded computing capability and the efficient machine vision system, the robot can inherit the learned behavior from a simulator which has learned the empirical behavior and continue to learn with Q-learning to improve the performance of target seeking problem.Integration Technology, 2007. ICIT '07. IEEE International Conference on; 04/2007 -
Conference Proceeding: Q-Learning with FCMAC in Multi-agent Cooperation.
Advances in Neural Networks - ISNN 2006, Third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006, Proceedings, Part I; 01/2006 -
Conference Proceeding: A grey evaluation function for reinforcement learning
[show abstract] [hide abstract]
ABSTRACT: A self-organizing control mechanism with a capability of reinforcement learning is proposed. The method is realized by a reinforcement signal predictor based on the grey theory and a policy learning unit implemented by a neural network. In consideration of the stability problem in learning, temporal difference algorithm is used as the weight-update rule of the connectionist. From the results of the simulations and experiments, the proposed method demonstrates that a control task can be learned even with very little a priori knowledge.Neural Networks and Signal Processing, 2003. Proceedings of the 2003 International Conference on; 01/2004 -
Article: Autonomous Exploring System Based on Ultrasonic Sensory Information.
Journal of Intelligent and Robotic Systems. 01/2004; 39:307-331. -
Article: Speed alteration strategy for multijoint robots in co-working environment
[show abstract] [hide abstract]
ABSTRACT: A collision-free trajectory planning method based on speed alternation strategy for multijoint manipulators in overlapped working envelopes is proposed. Since the shape of a robot's link is usually rectangular or cylindrical approximately, the proposed method models a robot's link mathematically by quadric primitives, such as ellipsoids and spheres. The occurrence of collisions between links can be predicted easily by means of relative coordinate transformations and geometric deformations between those ellipsoids. Furthermore, the collision-trend index which is defined by projecting the ellipsoids geometrically onto the Gaussian distribution plays a significant role in searching the optimal resolution in the proposed collision-avoidance method. Experiments with two Motoman robots from the YASUKAWAI Company are conducted to demonstrate the performance of the proposed methods.IEEE Transactions on Industrial Electronics 05/2003; · 5.16 Impact Factor
Top co-authors
Top Journals
Institutions
-
2003
-
National Chung Cheng University
Xinying, Taiwan, Taiwan
-
