Hierarchical Architecture with Modular Network SOM and Modular Reinforcement Learning
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Brain-inspired emergence of behaviors based on the desire for existence by reinforcement learning
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Multi-robot formation control using reinforcement learning method
ICSI'10 Proceedings of the First international conference on Advances in Swarm Intelligence - Volume Part I
Hi-index | 0.00 |
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.