Deep learning (DL) and reinforcement learning (RL) methods seem to be a part of
indispensable factors to achieve human-level or super-human AI systems. On the other …

This paper presents a computational theory on the roles of the ascending neuromodulatory
systems from the viewpoint that they mediate the global signals that regulate the distributed …

General-purpose robotic systems must master a large repertoire of diverse skills to be useful
in a range of daily tasks. While reinforcement learning provides a powerful framework for …

Legged robots pose one of the greatest challenges in robotics. Dynamic and agile
maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A …

Reinforcement learning offers to robotics a framework and set of tools for the design of
sophisticated and hard-to-engineer behaviors. Conversely, the challenges of robotic …

In this paper, we suggest that cortical anatomy recapitulates the temporal hierarchy that is
inherent in the dynamics of environmental states. Many aspects of brain function can be …

We propose a modular reinforcement learning architecture for nonlinear, nonstationary
control tasks, which we call multiple model-based reinforcement learning (MMRL). The basic …

Many reinforcement learning (RL) tasks, especially in robotics, consist of multiple sub-tasks
that are strongly structured. Such task structures can be exploited by incorporating …

In Exploring Robotic Minds: Actions, Symbols, and Consciousness as Self-Organizing
Dynamic Phenomena, Jun Tani sets out to answer an essential and tantalizing question …

This letter proposes a new reinforcement learning (RL) paradigm that explicitly takes into
account input disturbance as well as modeling errors. The use of environmental models in …