Demo video: Towers of Saliency
Deep reinforcement learning (DRL) has had many successes on complex tasks, but is typically considered a black box. Opening this black box would enable better understanding and trust of the model which can be helpful for researchers and end users to better interact with the learner. In this paper, we propose a new visualization to better analyze DRL agents and present a case study using the Pommerman benchmark domain. This visualization combines two previously proven methods for improving human un-derstanding of systems: saliency mapping and immersive visualization.
Bibtex
@inproceedings{Douglas2019,
author = {Douglas, Nathan and Yim, Dianna and Kartal, Bilal and Hernandez-Leal, Pablo and Taylor, Matthew E. and Maurer, Frank},
title = {Towers of Saliency: A Reinforcement Learning Visualization Using Immersive Environments},
booktitle = {Proceedings of the 2019 ACM International Conference on Interactive Surfaces and Spaces},
series = {ISS '19},
year = {2019},
isbn = {978-1-4503-6891-9/19/11},
location = {Daejon, Republic of Korea},
numpages = {4},
publisher = {ACM},
address = {New York, NY, USA},
}
Related Research
-
Our NeurIPS 2021 Reading List
Our NeurIPS 2021 Reading List
Y. Cao, K. Y. C. Lui, T. Durand, J. He, P. Xu, N. Mehrasa, A. Radovic, A. Lehrmann, R. Deng, A. Abdi, M. Schlegel, and S. Liu.
Computer Vision; Data Visualization; Graph Representation Learning; Learning And Generalization; Natural Language Processing; Optimization; Reinforcement Learning; Time series Modelling; Unsupervised Learning
Research
-
Heterogeneous Multi-task Learning with Expert Diversity
Heterogeneous Multi-task Learning with Expert Diversity
G. Oliveira, and F. Tung.
Computer Vision; Natural Language Processing; Reinforcement Learning
Research
-
Desired characteristics for real-world RL agents
Desired characteristics for real-world RL agents
P. Hernandez-Leal, and Y. Gao.
Research