Robots that can adapt and perform multiple tasks promise to be a powerful tool with many applications. In order to achieve such robots, control systems have to be constructed that...
This paper presents a novel method for on-line coordination in multiagent reinforcement learning systems. In this method a reinforcement-learning agent learns to select its action ...
— Traditional approaches to programming robots are generally inaccessible to non-robotics-experts. A promising exception is the Learning from Demonstration paradigm. Here a polic...
CT How can an adaptive intelligent interface decide what particular action to perform in a given situation, as a function of perceived properties of the user and the situation? Ide...
Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches to this goal du...