Brain-Inspired Emergence of Behaviors in Mobile Robots by Reinforcement Learning with Internal Rewards

Abstract

To develop truly autonomous mobile robots, we propose to introduce internal rewards such as the desire for existence, specific curiosity, diversive curiosity, boredom, and novelty into reinforcement learning. They are expected to make mobile robots capable of behaving appropriately without being told what to do. Firstly, we propose to use multiple sources of rewards to endow mobile robots with ability to behave properly in the real world. Secondly, we propose task-independent internal rewards. Thirdly, we propose to attain engineering merit of internal rewards, in addition to scientific interest. A pursuit-evasion game comprising a predator and its prey on a robotic field is selected as a testbed. Simulation experiments as well as real experiments using mobile robots, WITHs, well demonstrate the utility and benefit of internal rewards in reinforcement learning.