Comparison of Reinforcement Learning Activation Functions to Improve the Performance of the Racing Game Learning Agent


Dongcheul Lee, Journal of Information Processing Systems Vol. 16, No. 5, pp. 1074-1082, Oct. 2020  

10.3745/JIPS.02.0141
Keywords: Activation Function, Racing Game, Reinforcement Learning
Fulltext:

Abstract

Recently, research has been actively conducted to create artificial intelligence agents that learn games through reinforcement learning. There are several factors that determine performance when the agent learns a game, but using any of the activation functions is also an important factor. This paper compares and evaluates which activation function gets the best results if the agent learns the game through reinforcement learning in the 2D racing game environment. We built the agent using a reinforcement learning algorithm and a neural network. We evaluated the activation functions in the network by switching them together. We measured the reward, the output of the advantage function, and the output of the loss function while training and testing. As a result of performance evaluation, we found out the best activation function for the agent to learn the game. The difference between the best and the worst was 35.4%.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Dongcheul Lee (2020). Comparison of Reinforcement Learning Activation Functions to Improve the Performance of the Racing Game Learning Agent. Journal of Information Processing Systems, 16(5), 1074-1082. DOI: 10.3745/JIPS.02.0141.

[IEEE Style]
D. Lee, "Comparison of Reinforcement Learning Activation Functions to Improve the Performance of the Racing Game Learning Agent," Journal of Information Processing Systems, vol. 16, no. 5, pp. 1074-1082, 2020. DOI: 10.3745/JIPS.02.0141.

[ACM Style]
Dongcheul Lee. 2020. Comparison of Reinforcement Learning Activation Functions to Improve the Performance of the Racing Game Learning Agent. Journal of Information Processing Systems, 16, 5, (2020), 1074-1082. DOI: 10.3745/JIPS.02.0141.