Mulawade, Raju NingappaGarth, ChristophWiebel, AlexanderArchambault, DanielNabney, IanPeltonen, Jaakko2022-06-022022-06-022022978-3-03868-182-3https://doi.org/10.2312/mlvis.20221069https://diglib.eg.org:443/handle/10.2312/mlvis20221069We develop and describe saliency clouds, that is, visualization methods employing explainable AI methods to analyze and interpret deep reinforcement learning (DeepRL) agents working on point cloud-based data. The agent in our application case is tasked to track particles in high energy physics and is still under development. The point clouds contain properties of particle hits on layers of a detector as the input to reconstruct the trajectories of the particles. Through visualization of the influence of different points, their possible connections in an implicit graph, and other features on the decisions of the policy network of the DeepRL agent, we aim to explain the decision making of the agent in tracking particles and thus support its development. In particular, we adapt gradient-based saliency mapping methods to work on these point clouds. We show how the properties of the methods, which were developed for image data, translate to the structurally different point cloud data. Finally, we present visual representations of saliency clouds supporting visual analysis and interpretation of the RL agent's policy network.Attribution 4.0 International LicenseCCS Concepts: Human-centered computing --> Visualization techniques; Computing methodologies --> Neural networksHuman centered computingVisualization techniquesComputing methodologiesNeural networks10.2312/mlvis.202210697-115 pages