4 papers
Revisiting Action Factorization for Complex Action Spaces
Timothy Flavin, Sandip Sen
Many real-world control problems involve hybrid discrete-continuous action spaces. For example, steering and signaling in autonomous driving, and aiming and firing in robotics or v…
A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations
Timothy Flavin, Sandip Sen
Reinforcement Learning (RL) algorithms exhibit high sample complexity, particularly when applied to Decentralized Partially Observable Markov Decision Processes (Dec-POMDPs). As a…
Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability
Joe Shymanski, Jacob Brue, Sandip Sen
Explainable AI (XAI) presents useful tools to facilitate transparency and trustworthiness in machine learning systems. However, current evaluations of system explainability often r…
Not All Explanations are Created Equal: Investigating the Pitfalls of Current XAI Evaluation
Joe Shymanski, Jacob Brue, Sandip Sen
Explainable Artificial Intelligence (XAI) aims to create transparency in modern AI models by offering explanations of the models to human users. There are many ways in which resear…