RESUMO
Nowadays, Artificial Intelligence systems have expanded their competence field from research to industry and daily life, so understanding how they make decisions is becoming fundamental to reducing the lack of trust between users and machines and increasing the transparency of the model. This paper aims to automate the generation of explanations for model-free Reinforcement Learning algorithms by answering "why" and "why not" questions. To this end, we use Bayesian Networks in combination with the NOTEARS algorithm for automatic structure learning. This approach complements an existing framework very well and demonstrates thus a step towards generating explanations with as little user input as possible. This approach is computationally evaluated in three benchmarks using different Reinforcement Learning methods to highlight that it is independent of the type of model used and the explanations are then rated through a human study. The results obtained are compared to other baseline explanation models to underline the satisfying performance of the framework presented in terms of increasing the understanding, transparency and trust in the action chosen by the agent.
RESUMO
The dataset for Multi Depot Dynamic Vehicle Routing Problem with Stochastic Road Capacity (MDDVRPSRC) is presented in this paper. The data consist of 10 independent designs of evolving road networks ranging from 14-49 nodes. Together with the road networks are the Damage file (DF) for each corresponding road network. The DF simulates the damage level of roads within the networks due to a disaster source, thus affecting travel time and road capacity. We applied this data to test our proposed algorithm and validate our proposed model. This dataset served as an addition to the Vehicle Routing Problem (VRP) datasets that specifically addressed the road capacity problem during a disaster from an epicentre and could be used for other applications that constitute chaotic events and compromised road networks.
