Cyber Rodent Project

• Research
• People
• Publications
• Hardware
• Photos
• Movies
• Related Links
• Contact

Recent advances in artificial neural networks and machine learning have allowed us to build robots and virtual agents that can learn a variety of goal-directed behaviors. However the performance of learning systems depends critically on

1. metaparameters that controls how the detailed system parameters change with learning,
2. reward functions to be learned,
3. state space representation, and
4. learning algorithms used by the learning agent.

In many applications human experts design and tune th above issues by trial and error. The need for careful design of them is one of the major reasons why the intelligent robots can not perform well in the real environment. Compared to current artificial learning systems, humans and animals can learn novel behaviors under a wide variety of environments under the basic constraints: self-preservation and self-reproduction.

The goal of the Cyber Rodent project is to understand neural mechanisms necessary for the artificial agents that have the same fundamental constraints as biological agents: self-preservation and self-reproduction.

Based on the theories of reinforcement learning and evolutionary computation, we exlore parallel learning mechanisms using a colony of small rodent-like mobile robots called Cyber Rodents.

The Cyber Rodent robot has an omnidirectional vision system as its eye, infra-red proximity sensors as its whiskers, two wheels for locomotion, and a three-color LED for emotional communication. Especially it has the capabilities of recharging from external battery packs and exchanging gene (program or data) via IR-ports.

We aim to develop computational frameworks for autonomously adapting these factors in biologically plausible manners. Our research topics include the following:

1. Evolution of neural controllers
2. Evolution of meta-parameters in reinforcement learning
3. Evolution of hierarchical architectures in reinforcement learning
4. Evolution of the reward function that enable efficient learning and evolution
5. Cooperation and Competition of Multiple Heterogeneous Reinforcement Learners Sharing the Same Sensory-Motor System

See also Research Topic if you are interested in the deatils.