— A decentralized controller is presented that causes a network of robots to converge to a near optimal sensing configuration, while simultaneously learning the distribution of ...
Mac Schwager, Jean-Jacques E. Slotine, Daniela Rus
—Large-scale agent-based systems are required to self-optimize towards multiple, potentially conflicting, policies of varying spatial and temporal scope. As a result, not all ag...
Abstract. In this paper we study distributed online learning of locomotion gaits for modular robots. The learning is based on a stochastic approximation method, SPSA, which optimiz...
Abstract. This paper proposes an algorithm for combinatorial optimizations that uses reinforcement learning and estimation of joint probability distribution of promising solutions ...
Abstract. A key problem in designing artificial neural networks for visual object recognition tasks is the proper choice of the network architecture. Evolutionary optimization met...
Georg Schneider, Heiko Wersing, Bernhard Sendhoff,...