SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mishra, Satyam, Vi, Phung Thao, Mishra, Shivam, Bijalwan, Vishwanath, Semwal, Vijay Bhaskar, Khan, Abdul Manan
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908415070044160
author Mishra, Satyam
Vi, Phung Thao
Mishra, Shivam
Bijalwan, Vishwanath
Semwal, Vijay Bhaskar
Khan, Abdul Manan
author_facet Mishra, Satyam
Vi, Phung Thao
Mishra, Shivam
Bijalwan, Vishwanath
Semwal, Vijay Bhaskar
Khan, Abdul Manan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17297
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library
Mishra, Satyam
Vi, Phung Thao
Mishra, Shivam
Bijalwan, Vishwanath
Semwal, Vijay Bhaskar
Khan, Abdul Manan
Machine Learning
Artificial Intelligence
68T05
I.2.6; I.2.8
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.
title SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library
topic Machine Learning
Artificial Intelligence
68T05
I.2.6; I.2.8
url https://arxiv.org/abs/2506.17297