Designing Intelligent Systems with Reinforcement Learning
Reinforcement learning (RL) is an AI technique that learns through trial and error, controlling an intelligent agent so that it can respond flexibly to a wide variety of situations.
For example, both videos on the right show vehicle control learned with reinforcement learning — but which one looks more intelligent? The lower one probably looks smarter, yet the upper one is actually doing something harder. The upper agent directly controls the steering angle and acceleration from its lane deviation and its distance to surrounding vehicles, whereas the lower agent does not learn vehicle control at all: from its spatial relationship to other vehicles, it learns only the high-level decision of whether to go, ease off, or stop.
So why does such a difference arise between systems that both use reinforcement learning? The key lies in system design. In this scene the objective is simply “follow the lane,” and since a well-established control law already exists, the flexibility of AI is really only needed for avoiding collisions with the vehicle ahead. Making even the vehicle control flexible, as in the upper system, therefore takes longer before the agent drives well. Of course, with more training the upper system may also achieve good control, and in more complex scenes such as intersections — where intricate decision-making and vehicle control are needed at the same time — the flexibility of reinforcement learning becomes essential for the vehicle control itself.
In our laboratory, we design “smart” intelligent systems that take these problem characteristics into account, and we aim to develop “flexible” reinforcement learning models that view the system as a whole and adapt to the diverse characteristics of a problem. We then explore how to solve real-world problems where introducing AI is difficult, by extending the capabilities of such intelligent systems through their flexibility. In particular, we study the fundamentals and applications of multi-agent reinforcement learning, targeting systems in which multiple active units — such as vehicles and robots — coexist.
Research Areas
SOFT Research Themes
Multi-Agent Reinforcement Learning and Smart Mobility
Multi-agent reinforcement learning for safe route optimisation of multiple vessels and path planning for aerial delivery robots.
Learn more →Distributional Reinforcement Learning
Enhancing distributional reinforcement learning, which learns by estimating the distribution of obtained rewards.
Learn more →Explainable AI for Robot Control
Investigating flexible robot control based on Learning Classifier Systems, which learn from sets of rules.
Learn more →Multi-Objective Multi-Agent Reinforcement Learning
Multi-objective multi-agent reinforcement learning for solving complex, real-world problems.
Learn more →LLM-Driven Reinforcement Learning
Using large language models to enhance reinforcement learning.
Learn more →