In complex distributed applications, a problem is often decomposed into a set of subproblems that are distributed to multiple agents. We formulate this class of problems with a tw...
Universal induction solves in principle the problem of choosing a prior to achieve optimal inductive inference. The AIXI theory, which combines control theory and universal induct...
Representation is a fluent. A mismatch between the real world and an agent's representation of it can be signalled by unexpected failures (or successes) of the agent's r...
An agent operating in an unpredictable world must be able to take advantage of opportunities but cannot afford to perform a detailed analysis of the effects of every nuance of the...
Members of high-performing human teams can often anticipate information needs of teammates and offer relevant information to them proactively. Such capabilities are highly desirab...