Abstract: Reinforcement learning has shown great success in controlling complex dynamical systems. However, when training a policy, most algorithms only consider a single objective function. While this may suffice in virtual domains, physical systems must satisfy a set of operational constraints, with safety being of crucial importance. It is natural to express these problems as
Abstract: The social structure and behaviour of organisms is highly divergent. How can this stunning diversity in nature be explained? I will argue that a few key principles are responsible for the evolution of social behaviour, with all its simple and complex manifestations. Organisms compete for resources. As survival and reproduction require resources and only
Consensus algorithms are routinely employed in a variety of multi-agent scenarios. They require that each agent iteratively evaluates a multivariate function of its neighbours’ information states. If a wireless communication channel is used, this is typically implemented through protocols (such as TDMA – Time Division Multiple Access) that avoid superposition of transmitted signals by assigning each transmitter its own
Marchstr. 23 – MAR 5-2
10587 Berlin
Email: info@scioi.de
Tel: +49 30 314 70660
