We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Gradient-based numerical optimization of complex engineering designs offers the promise of rapidly producing better designs. However, such methods generally assume that the object...
Background: Prediction of disulfide bridges from protein sequences is useful for characterizing structural and functional properties of proteins. Several methods based on differen...
Marc Vincent, Andrea Passerini, Matthieu Labb&eacu...
A major goal for AI is to allow users to interact with agents that learn in real time, making new kinds of interactive simulations, training applications, and digital entertainmen...
Kenneth O. Stanley, Bobby D. Bryant, Igor Karpov, ...
It is difficult to apply machine learning to new domains because often we lack labeled problem instances. In this paper, we provide a solution to this problem that leverages domai...