English

Explainable Artificial Intelligence (XAI) for Increasing User Trust in Deep Reinforcement Learning Driven Autonomous Systems

Artificial Intelligence 2021-06-08 v1 Machine Learning

Abstract

We consider the problem of providing users of deep Reinforcement Learning (RL) based systems with a better understanding of when their output can be trusted. We offer an explainable artificial intelligence (XAI) framework that provides a three-fold explanation: a graphical depiction of the systems generalization and performance in the current game state, how well the agent would play in semantically similar environments, and a narrative explanation of what the graphical information implies. We created a user-interface for our XAI framework and evaluated its efficacy via a human-user experiment. The results demonstrate a statistically significant increase in user trust and acceptance of the AI system with explanation, versus the AI system without explanation.

Keywords

Cite

@article{arxiv.2106.03775,
  title  = {Explainable Artificial Intelligence (XAI) for Increasing User Trust in Deep Reinforcement Learning Driven Autonomous Systems},
  author = {Jeff Druce and Michael Harradon and James Tittle},
  journal= {arXiv preprint arXiv:2106.03775},
  year   = {2021}
}

Comments

NeurIPS Deep RL workshop, Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada

R2 v1 2026-06-24T02:55:23.306Z