From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable ai
The rising popularity of explainable artificial intelligence (XAI) to understand high-performing
black boxes raised the question of how to evaluate explanations of machine learning (ML) …
black boxes raised the question of how to evaluate explanations of machine learning (ML) …
Explainable reinforcement learning: A survey and comparative review
Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine
learning that has attracted considerable attention in recent years. The goal of XRL is to …
learning that has attracted considerable attention in recent years. The goal of XRL is to …
The emerging landscape of explainable ai planning and decision making
T Chakraborti, S Sreedharan… - arXiv preprint arXiv …, 2020 - arxiv.org
In this paper, we provide a comprehensive outline of the different threads of work in
Explainable AI Planning (XAIP) that has emerged as a focus area in the last couple of years …
Explainable AI Planning (XAIP) that has emerged as a focus area in the last couple of years …
A survey of explainable reinforcement learning
Explainable reinforcement learning (XRL) is an emerging subfield of explainable machine
learning that has attracted considerable attention in recent years. The goal of XRL is to …
learning that has attracted considerable attention in recent years. The goal of XRL is to …
Human–autonomy teaming: Definitions, debates, and directions
Researchers are beginning to transition from studying human–automation interaction to
human–autonomy teaming. This distinction has been highlighted in recent literature, and …
human–autonomy teaming. This distinction has been highlighted in recent literature, and …
Accountability in offline reinforcement learning: Explaining decisions with a corpus of examples
Learning controllers with offline data in decision-making systems is an essential area of
research due to its potential to reduce the risk of applications in real-world systems …
research due to its potential to reduce the risk of applications in real-world systems …
Statemask: Explaining deep reinforcement learning through state mask
Despite the promising performance of deep reinforcement learning (DRL) agents in many
challenging scenarios, the black-box nature of these agents greatly limits their applications …
challenging scenarios, the black-box nature of these agents greatly limits their applications …
Validating metrics for reward alignment in human-autonomy teaming
L Sanneman, JA Shah - Computers in Human Behavior, 2023 - Elsevier
Alignment of human and autonomous agent values and objectives is vital in human-
autonomy teaming settings which require collaborative action toward a common goal. In …
autonomy teaming settings which require collaborative action toward a common goal. In …
Ganterfactual—counterfactual explanations for medical non-experts using generative adversarial learning
With the ongoing rise of machine learning, the need for methods for explaining decisions
made by artificial intelligence systems is becoming a more and more important topic …
made by artificial intelligence systems is becoming a more and more important topic …
Explainability in deep reinforcement learning: A review into current methods and applications
T Hickling, A Zenati, N Aouf, P Spencer - ACM Computing Surveys, 2023 - dl.acm.org
The use of Deep Reinforcement Learning (DRL) schemes has increased dramatically since
their first introduction in 2015. Though uses in many different applications are being found …
their first introduction in 2015. Though uses in many different applications are being found …