The paper formalizes a distributed approach to the problem of supervising the execution of a multi-agent plan where (possibly joint) actions are executed concurrently by a team of...
A central problem in artificial intelligence is to choose actions to maximize reward in a partially observable, uncertain environment. To do so, we must learn an accurate model of ...
Planning in large, partially observable domains is challenging, especially when a long-horizon lookahead is necessary to obtain a good policy. Traditional POMDP planners that plan...
Planning for partially observable, nondeterministic domains is a very signi cant and computationally hard problem. Often, reasonable assumptions can be drawn over expected/nominal...
For a given problem, the optimal Markov policy over a finite horizon is a conditional plan containing a potentially large number of branches. However, there are applications wher...