Venue
- XAI.it 2023 @ AIXIA
Date
- 2023
Understanding Deep RL agent decisions: a novel interpretable approach with trainable prototypes
Caterina Borzillo*
Alessio Ragno*
* External authors
XAI.it 2023 @ AIXIA
2023
Abstract
Deep reinforcement learning (DRL) models have shown great promise in various applications, but their practical adoption in critical domains is limited due to their opaque decision-making processes. To address this challenge, explainable AI (XAI) techniques aim to enhance transparency and interpretability of black-box models. However, most current interpretable systems focus on supervised learning problems, leaving reinforcement learning relatively unexplored. This paper extends the work of PW-Net, an interpretable wrapper model for DRL agents inspired by image classification methodologies. We introduce Shared-PW-Net, an interpretable deep learning model that features a fully trainable prototype layer. Unlike PW-Net, Shared-PW-Net does not rely on pre-existing prototypes. Instead, it leverages the concept of ProtoPool to automatically learn general prototypes assigned to actions during training. Additionally, we propose a novel prototype initialization method that significantly improves the model’s performance. Through extensive experimentation, we demonstrate that our Shared-PW-Net achieves the same reward performance as existing methods without requiring human intervention. Our model’s fully trainable prototype layer, coupled with the innovative prototype initialization approach, contributes to a clearer and more interpretable decision-making process. The code for this work is publicly available for further exploration and applications.
Related Publications
We employ sequences of high-order motion primitives for efficient online trajectory planning, enabling competitive racecar control even when the car deviates from an offline demonstration. Dynamic Movement Primitives (DMPs) utilize a target-driven non-linear differential equ…
Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations used to check the alignment (i.e., the highest ones), thus lacking c…
Two of the most impressive features of biological neural networks are their high energy efficiency and their ability to continuously adapt to varying inputs. On the contrary, the amount of power required to train top-performing deep learning models rises as they become more …
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.