odel of Embodiment on Abstract Systems: from Hierarchy to Heterarchy Kohei Nakajima, Soya Shinkai, Takashi Ikegami A Behavior-Based Model of the Hydra, Phylum Cnidaria Malin Aktius...
TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD...
Multiarmed bandit problem is a typical example of a dilemma between exploration and exploitation in reinforcement learning. This problem is expressed as a model of a gambler playi...
We introduce flexible algorithms that can automatically learn mappings from images to actions by interacting with their environment. They work by introducing an image classifier i...
Creating coordinated multiagent policies in environments with uncertainty is a challenging problem, which can be greatly simplified if the coordination needs are known to be limi...