Coordination of distributed agents is required for problems arising in m...
We consider the problem of optimal planning in stochastic domains with
r...
A limited-memory influence diagram (LIMID) generalizes a traditional
inf...
Most algorithms for solving POMDPs iteratively improve a value function ...
Symbolic representations have been used successfully in off-line plannin...
Bounded policy iteration is an approach to solving infinite-horizon POMD...
A branch-and-bound approach to solving influ- ence diagrams has been
pre...
Previous work has shown that the problem of learning the optimal structu...
We consider how to use the Bellman residual of the dynamic programming
o...