Authors

* External authors

Venue

Date

Share

Understanding Deep RL agent decisions: a novel interpretable approach with trainable prototypes

Caterina Borzillo*

Alessio Ragno*

Roberto Capobianco

* 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

Identifying Candidates for Protein-Protein Interaction: A Focus on NKp46’s Ligands

EXPLIMED, 2025
Alessia Borghini, Federico Di Valerio, Alessio Ragno*, Roberto Capobianco

Recent advances in protein-protein interaction (PPI) research have harnessed the power of artificialintelligence (AI) to enhance our understanding of protein behaviour. These approaches have becomeindispensable tools in the field of biology and medicine, enabling scientists …

Neural Reward Machines

ECAI, 2025
Elena Umili*, Francesco Argenziano*, Roberto Capobianco

Non-markovian Reinforcement Learning (RL) tasks arevery hard to solve, because agents must consider the entire history ofstate-action pairs to act rationally in the environment. Most works usesymbolic formalisms (as Linear Temporal Logic or automata) to specify the temporall…

Transparent Explainable Logic Layers

ECAI, 2025
Alessio Ragno*, Marc Plantevit, Celine Robardet, Roberto Capobianco

Explainable AI seeks to unveil the intricacies of black box models through post-hoc strategies or self-interpretable models. In this paper, we tackle the problem of building layers that are intrinsically explainable through logical rules. In particular, we address current st…

  • HOME
  • Publications
  • Understanding Deep RL agent decisions: a novel interpretable approach with trainable prototypes

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.