Continuous Valued Q-learning for Vision-Guided Behavior Acquisition

Improvement Continuous Valued Q-learning and Its Application to Vision Guided Behavior Acquisition

Q-learning, a most widely used reinforcement learning method, normally needs well-de ned quantized state and action spaces to converge. This makes it di cult to be applied to real robot tasks because of poor performance of learned behavior and further a new problem of state space construction. We have proposed Continuous Valued Q-learning for real robot applications, which calculates contributi...

Continuous Valued Q-learning for Vision-Guided Behavior A quisition

Enhanced continuous valued Q-learning for real autonomous robots

Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to obtain an optimal policy for accomplishing a given task. This makes it difficult to be applied to real robot tasks because of poor performance of learned behavior due to the failure of quantization of continuous state and action spaces. To deal with this problem, we pro...

An Application of Vision-Based Learning for a Real Robot in RoboCup - A Goal Keeping Behavior for a Robot with an Omnidirectional Vision and an Embedded Servoing

We have applied Q-learning method so that a mobile robot acquire a shooting behavior of a soccer game. Thought the acquired behavior is tested in RoboCup-97, the performance is limited because of the narrow visual angle of the robot. Therefore, we install an omnidirectional vision into a mobile robot to enlarge a visual angle and apply Q-learning to behavior acquisition of the robot. An attenti...

Acquisition of Visual Motion Guided Behaviors

Sensor and motor systems are not separable for autonomous agents to accomplish tasks in a dynamic environment. However, almost computer vision researchers have not investigated the relationship between the low level motion representation and the visual information. In this paper, we propose a method by which a mobile robot learns sensorimotor apparatus and target pursuit behavior without any ca...