Much emphasis in multiagent reinforcement learning (MARL) research is placed on ensuring that MARL algorithms (eventually) converge to desirable equilibria. As in standard reinfor...
Auctions are useful mechanism for allocating items (goods, tasks, resources, etc.) in multiagent systems. The bulk of auction theory assumes that the bidders’ valuations for ite...
— We consider the control of impulsive systems with jumps triggered by a renewal process, that is, the intervals between jumps are independent and identically distributed. The co...
An agent that deviates from a usual or previous course of action can be said to display novel or varying behaviour. Novelty of behaviour can be seen as the result of real or appar...
In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning e ective behaviors in a complex enviro...