摘要 |
In one exemplary embodiment, a method includes: modeling, by at least one processor, a problem as an approximated exogenous Markov decision process (X-MDP); converting, by the at least one processor, the approximated X-MDP into a Markov decision process (MDP); solving, by the at least one processor, the MDP using at least one search algorithm to obtain a decision; and returning, by the at least one processor, the decision.
|