Timezone: »

 
Poster
Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning
Guiliang Liu · Xiangyu Sun · Oliver Schulte · Pascal Poupart

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @
in Poster Session 2 »

Interpreting Deep Reinforcement Learning (DRL) models is important to enhance trust and comply with transparency regulations. Existing methods typically explain a DRL model by visualizing the importance of low-level input features with super-pixels, attentions, or saliency maps. Our approach provides an interpretation based on high-level latent object features derived from a disentangled representation. We propose a Represent And Mimic (RAMi) framework for training 1) an identifiable latent representation to capture the independent factors of variation for the objects and 2) a mimic tree that extracts the causal impact of the latent features on DRL action values. To jointly optimize both the fidelity and the simplicity of a mimic tree, we derive a novel Minimum Description Length (MDL) objective based on the Information Bottleneck (IB) principle. Based on this objective, we describe a Monte Carlo Regression Tree Search (MCRTS) algorithm that explores different splits to find the IB-optimal mimic tree. Experiments show that our mimic tree achieves strong approximation performance with significantly fewer nodes than baseline models. We demonstrate the interpretability of our mimic tree by showing latent traversals, decision rules, causal impacts, and human evaluation results.

Keywords: Reinforcement Learning and Planning · Interpretability

Author Information

Guiliang Liu (University of Waterloo)
Xiangyu Sun (Simon Fraser University)
Oliver Schulte (Simon Fraser University)
Oliver Schulte

Bio: Oliver Schulte is a Professor in the School of Computing Science at Simon Fraser University, Vancouver, Canada. He received his Ph.D. from Carnegie Mellon University in 1997. His current research focuses on machine learning for structured, relational, and event data. He has published sports analytics papers in leading AI and machine learning venues, and co-organized two hockey analytics conferences. The last two years he has worked with Sportlogiq, a leading hockey data provider. While he has won some nice awards, his biggest claim to fame may be a draw against chess world champion Gary Kasparov.

Pascal Poupart (University of Waterloo & Vector Institute)

More from the Same Authors