Exploration Methods in Reinforcement Learning
Bingjie Shen · 2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · 2022
Exploration and exploitation serve as cornerstones of reinforcement learning. The performance of agent is highly dependent on the exploration to obtain useful information in the unknown environment, which can be exploited to optimize the agent. Thus, the trade-off between exploration and exploitation is an essential problem in reinforcement learning. In this paper, we focus on the various exploration methods in reinforcement learning and discuss the strengths and weaknesses of these methods.