Franco Ruggeri | Searcharxiv

arXiv2025

Self-Explaining Reinforcement Learning for Mobile Network Resource Allocation

Deep reinforcement learning (DRL) methods, though powerful, often lack transparency, which limits their adoption in critical domains. We apply Self-Explaining Neural Networks (SENNs) to RL by parametrizing the policy of a PPO agent with a SENN, producing intrinsic local explanations, and propose a method for aggregating them into global explanations. We evaluate our approach on a mobile network resource allocation problem, our approach performs within a small margin of the state-of-the-art deep learning method and significantly outperforms the best deployed heuristic, while the extracted global explanations correlate strongly with DeepLift and InputXGradient, making SENNs a promising candidate for high-stakes RL.

cs.LG↗

arXiv2025

Explainable Reinforcement Learning via Temporal Policy Decomposition

We investigate the explainability of Reinforcement Learning (RL) policies from a temporal perspective, focusing on the sequence of future outcomes associated with individual actions. In RL, value functions compress information about rewards collected across multiple trajectories and over an infinite horizon, allowing a compact form of knowledge representation. However, this compression obscures the temporal details inherent in sequential decision-making, presenting a key challenge for interpretability. We present Temporal Policy Decomposition (TPD), a novel explainability approach that explains individual RL actions in terms of their Expected Future Outcome (EFO). These explanations decompose generalized value functions into a sequence of EFOs, one for each time step up to a prediction horizon of interest, revealing insights into when specific outcomes are expected to occur. We leverage fixed-horizon temporal difference learning to devise an off-policy method for learning EFOs for both optimal and suboptimal actions, enabling contrastive explanations consisting of EFOs for different state-action pairs. Our experiments demonstrate that TPD generates accurate explanations that (i) clarify the policy's future strategy and anticipated trajectory for a given action and (ii) improve understanding of the reward composition, facilitating fine-tuning of the reward function to align with human expectations.

cs.LG↗

arXiv1995

Nucleation Rate of Hadron Bubbles in Baryon-Free Quark-Gluon Plasma

We evaluate the factor $κ$ appearing in Langer's expression for the nucleation rate extended to the case of hadron bubbles forming in zero baryon number cooled quark-gluon plasma. We consider both the absence and presence of viscosity and show that viscous effects introduce only small changes in the value of $κ$

nucl-th↗