"so, Tell Me About Your Policy...": Distillation Of Interpretable Policies From Deep Reinforcement Learning Agents

Abstract

Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the ability to tackle complex games such as Atari, Go, and other real-world applications, including financial trading. Nevertheless, a significant challenge emerges from the lack of interpretability, particularly when attempting to comprehend the underlying patterns learned, the relative importance of the state features, and how they are integrated to generate the policy's output. For this reason, in mission-critical and real-world settings, it is often preferred to deploy a simpler and more interpretable algorithm, although at the cost of performance. In this paper, we propose a novel algorithm, supported by theoretical guarantees, that can extract an interpretable policy (e.g., a linear policy) without disregarding the peculiarities of expert behavior.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydispoto2025so

Related papers

• From Explainability To Interpretability: Interpretable Policies In Reinforcement Learning Via Model Explanation (2025)0.00
• Evaluating Interpretable Reinforcement Learning By Distilling Policies Into Programs (2025)0.00
• Fidelity-induced Interpretable Policy Extraction For Reinforcement Learning (2023)0.00
• S-REINFORCE: A Neuro-symbolic Policy Gradient Approach For Interpretable Reinforcement Learning (2023)0.00
• A Survey On Interpretable Reinforcement Learning (2021)0.00
• Continuous Action Reinforcement Learning From A Mixture Of Interpretable Experts (2020)0.00
• Verifiable Reinforcement Learning Via Policy Extraction (2018)0.00
• Synthesising Reinforcement Learning Policies Through Set-valued Inductive Rule Learning (2021)3.58