As agent systems are solving more and more complex tasks in increasingly challenging domains, the systems themselves are becoming more complex too, often compromising their adapti...
We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
A decision process in which rewards depend on history rather than merely on the current state is called a decision process with non-Markovian rewards (NMRDP). In decisiontheoretic...
We present the first hardware-in-the-loop evolutionary optimization on an ornithopter. Our experiments demonstrate the feasibility of evolving flight through genetic algorithms an...
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...