Evolution of meta-parameters in reinforcement learning algorithm

In most Reinforcment Learning approches, the metaparameters such as learning rate and ”temperatur” for exploration are adjusted manually. In order to build fully autonomous learning agents, it is important to develop methods for adjusting these parameters to match the demands of the task and the environment. In this paper, we propose a new method to determine the values of meta parameters in reinforcement learning, based on evolutionary approach. Simulations and experimental results with the Cyber Rodent robot show that meta parameters have a strong effect on agent performance and they are strongly related with each-other.