SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library
This provides a modular tool for researchers and practitioners in reinforcement learning to enforce safety constraints and improve interpretability, though it is incremental as it builds on existing methods.
The authors tackled the lack of native safety constraints and explainability in reinforcement learning toolkits by introducing SafeRL-Lite, a lightweight Python library that enables safety-aware training and real-time explanations, demonstrated on constrained CartPole variants with built-in metrics for constraint violations.
We introduce SafeRL-Lite, an open-source Python library for building reinforcement learning (RL) agents that are both constrained and explainable. Existing RL toolkits often lack native mechanisms for enforcing hard safety constraints or producing human-interpretable rationales for decisions. SafeRL-Lite provides modular wrappers around standard Gym environments and deep Q-learning agents to enable: (i) safety-aware training via constraint enforcement, and (ii) real-time post-hoc explanation via SHAP values and saliency maps. The library is lightweight, extensible, and installable via pip, and includes built-in metrics for constraint violations. We demonstrate its effectiveness on constrained variants of CartPole and provide visualizations that reveal both policy logic and safety adherence. The full codebase is available at: https://github.com/satyamcser/saferl-lite.