Nafiseh Didkar - Department of Computer Science Amirkabir University of TechnologyTehran, Iran
Zeinab Arabasadi
Mohammad Ebrahim Shiri

One of the problems in reinforcement learning is that as the environment becomes more complex, the number of parameters used in decision making increase which leads us to a slow decision making process. The main idea here is to come up with a new algorithm which is able to transfer the information, using data mining techniques in extracting the patterns. The state transitions and actions which happen during the transfer by the agent are saved as a data set for data mining techniques. The main idea is to use the repeated action in each state, as a pattern in similar states as a means to improve learning speed and performance. The results in our algorithm will be compared to the results in Q-learning algorithm.

Reinforcement learning; Transfer learning; Data Mining;