Transparent value alignment
L Sanneman, J Shah - Companion of the 2023 ACM/IEEE International …, 2023 - dl.acm.org
As robots become increasingly prevalent in our communities, aligning the values motivating
their behavior with human values is critical. However, it is often difficult or impossible for …
their behavior with human values is critical. However, it is often difficult or impossible for …
An Information Bottleneck Characterization of the Understanding-Workload Tradeoff in Human-Centered Explainable AI
Recent advances in artificial intelligence (AI) have underscored the need for explainable AI
(XAI) to support human understanding of AI systems. Consideration of human factors that …
(XAI) to support human understanding of AI systems. Consideration of human factors that …
An information bottleneck characterization of the understanding-workload tradeoff
Recent advances in artificial intelligence (AI) have underscored the need for explainable AI
(XAI) to support human understanding of AI systems. Consideration of human factors that …
(XAI) to support human understanding of AI systems. Consideration of human factors that …
[PDF][PDF] Closed-loop reasoning about counterfactuals to improve policy transparency
Explanations are a powerful way of increasing the transparency of complex AI policies. Such
explanations must not only be informative regarding the policy in question, but must also be …
explanations must not only be informative regarding the policy in question, but must also be …
Making AI Policies Transparent to Humans through Demonstrations
MS Lee - Proceedings of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
Demonstrations are a powerful way of increasing the transparency of AI policies to humans.
Though we can approximately model human learning from demonstrations as inverse …
Though we can approximately model human learning from demonstrations as inverse …
Closed-loop Teaching via Demonstrations to Improve Policy Transparency
Demonstrations are a powerful way of increasing the transparency of AI policies. Though
informative demonstrations may be selected a priori through the machine teaching …
informative demonstrations may be selected a priori through the machine teaching …
Understanding Robot Minds: Leveraging Machine Teaching for Transparent Human-Robot Collaboration Across Diverse Groups
In this work, we aim to improve transparency and efficacy in human-robot collaboration by
developing machine teaching algorithms suitable for groups with varied learning …
developing machine teaching algorithms suitable for groups with varied learning …
[PDF][PDF] Adaptive group machine teaching for human group inverse reinforcement learning
For safe and effective collaboration between a robot and a human group, the challenge
arises in teaching a diverse group of individuals about the robot's decision-making process …
arises in teaching a diverse group of individuals about the robot's decision-making process …
Transparent Value Alignment: Foundations for Human-Centered Explainable AI in Alignment
L Sanneman - 2023 - dspace.mit.edu
Alignment of autonomous agents' values and objectives with those of humans can greatly
enhance these agents' ability to act flexibly to safely and reliably meet humans' goals across …
enhance these agents' ability to act flexibly to safely and reliably meet humans' goals across …
[PDF][PDF] Improving the Transparency of Agent Decision Making to Humans Using Demonstrations
MS Lee - 2024 - ri.cmu.edu
For intelligent agents (eg robots) to be seamlessly integrated into human society, humans
must be able to understand their decision making. For example, the decision making of …
must be able to understand their decision making. For example, the decision making of …