Deep Q-network (DQN) is one of the most famous methods of deep reinforcement learning. DQN approximates the action value function by Convolutional Neural Network (CNN) and updates the action value function by Q-learning. In this research, we apply DQN to robot behavior learning the simulation environment. We realize that the mobile robot learns to acquire good behaviors such as avoiding the wall and moving along the center line by using high-dimensional visual information as input data. We propose a method which reuses the best target network so far in case learning performance suddenly falls. Moreover, we incorporate Profit Sharing method to DQN in order to accelerate the learning. Through the simulation experiment, we confirm the effectiveness of our method.
[1]
Alex Graves,et al.
Playing Atari with Deep Reinforcement Learning
,
2013,
ArXiv.
[2]
Shane Legg,et al.
Human-level control through deep reinforcement learning
,
2015,
Nature.
[3]
Martin A. Riedmiller.
Neural Fitted Q Iteration - First Experiences with a Data Efficient Neural Reinforcement Learning Method
,
2005,
ECML.
[4]
Yoshua Bengio,et al.
Gradient-based learning applied to document recognition
,
1998,
Proc. IEEE.
[5]
Osamu Katai,et al.
Q-PSP learning: an exploitation-oriented Q-learning algorithm and its applications
,
1996,
Proceedings of IEEE International Conference on Evolutionary Computation.