Learning From Scenarios for Stochastic Repairable Scheduling
This work addresses scheduling problems with uncertainty for operations research, but it is incremental as it adapts existing methods to a specific domain.
The paper tackles the problem of stochastic scheduling with uncertain processing times by adapting decision-focused learning techniques to handle constraints, and shows through experiments that it can outperform scenario-based stochastic optimization in certain situations.
When optimizing problems with uncertain parameter values in a linear objective, decision-focused learning enables end-to-end learning of these values. We are interested in a stochastic scheduling problem, in which processing times are uncertain, which brings uncertain values in the constraints, and thus repair of an initial schedule may be needed. Historical realizations of the stochastic processing times are available. We show how existing decision-focused learning techniques based on stochastic smoothing can be adapted to this scheduling problem. We include an extensive experimental evaluation to investigate in which situations decision-focused learning outperforms the state of the art for such situations: scenario-based stochastic optimization.