DVRPTW

Dynamic Capacitated Vehicle Routing Problem with Time Windows (DVRPTW)

The DCVRPTW is a generalization of the classical Capacitated Vehicle Routing Problem with Time Windows, incorporating uncertain and dynamic changes during operation: not all information is known offline, as the environment evolves due to dynamic customer requests that arrive sequentially while vehicles are en route, requiring that all vehicle capacity and customer time window constraints be met despite these dynamic changes (see [BONO2021]).

Here’s everything about DVRPTW environment:

• Agent Rewards
• Agent Selector
• Environment
• Generation
• Observations

References

[BONO2021]

Bono, G., Dibangoye, J. S., Simonin, O., Matignon, L., & Pereyron, F. (2021). Solving Multi-Agent Routing Problems Using Deep Attention Mechanisms. IEEE Transactions on Intelligent Transportation Systems, 22(12), 7804–7813;