SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems

• URL: http://arxiv.org/abs/2506.02255v1
• Date: Mon, 02 Jun 2025 20:59:45 GMT
• Title: SafeOR-Gym: A Benchmark Suite for Safe Reinforcement Learning Algorithms on Practical Operations Research Problems
• Authors: Asha Ramanujam, Adam Elyoumi, Hao Chen, Sai Madhukiran Kompalli, Akshdeep Singh Ahluwalia, Shraman Pal, Dimitri J. Papageorgiou, Can Li,
• Abstract summary: We present SafeOR-Gym, a benchmark suite of nine operations research (OR) environments tailored for safe RL under complex constraints.<n>Each environment captures a realistic planning, scheduling, or control problems characterized by cost-based constraint violations.<n>We evaluate several state-of-the-art safe RL algorithms across these environments, revealing a wide range of performance.
• Score: 6.009359914477515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most existing safe reinforcement learning (RL) benchmarks focus on robotics and control tasks, offering limited relevance to high-stakes domains that involve structured constraints, mixed-integer decisions, and industrial complexity. This gap hinders the advancement and deployment of safe RL in critical areas such as energy systems, manufacturing, and supply chains. To address this limitation, we present SafeOR-Gym, a benchmark suite of nine operations research (OR) environments tailored for safe RL under complex constraints. Each environment captures a realistic planning, scheduling, or control problems characterized by cost-based constraint violations, planning horizons, and hybrid discrete-continuous action spaces. The suite integrates seamlessly with the Constrained Markov Decision Process (CMDP) interface provided by OmniSafe. We evaluate several state-of-the-art safe RL algorithms across these environments, revealing a wide range of performance: while some tasks are tractable, others expose fundamental limitations in current approaches. SafeOR-Gym provides a challenging and practical testbed that aims to catalyze future research in safe RL for real-world decision-making problems. The SafeOR-Gym framework and all accompanying code are available at: https://github.com/li-group/SafeOR-Gym.

Related papers

• Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis [63.532413807686524]
  This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL) We propose a new architecture that handles the trade-off between efficient progress and safety during exploration.
  arXiv  Detail & Related papers  (2023-12-18T16:09:43Z)
• Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms [8.789204441461678]
  We present a solution of the safe exploration (GSE) problem in the form of a meta-algorithm for safe exploration, MASE. Our proposed algorithm achieves better performance than state-of-the-art algorithms on grid-world and Safety Gym benchmarks.
  arXiv  Detail & Related papers  (2023-10-05T00:47:09Z)
• GUARD: A Safe Reinforcement Learning Benchmark [11.887626936994883]
  Generalized Unified SAfe Reinforcement Learning Development Benchmark. GUARD is a generalized benchmark with a wide variety of RL agents, tasks, and safety constraint specifications. We present a comparison of state-of-the-art safe RL algorithms in various task settings using GUARD and establish baselines that future work can build on.
  arXiv  Detail & Related papers  (2023-05-23T04:40:29Z)
• OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research [3.0536277689386453]
  We introduce a foundational framework designed to expedite SafeRL research endeavors. Our framework encompasses an array of algorithms spanning different RL domains and places heavy emphasis on safety elements.
  arXiv  Detail & Related papers  (2023-05-16T09:22:14Z)
• A Multiplicative Value Function for Safe and Efficient Reinforcement Learning [131.96501469927733]
  We propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic. The safety critic predicts the probability of constraint violation and discounts the reward critic that only estimates constraint-free returns. We evaluate our method in four safety-focused environments, including classical RL benchmarks augmented with safety constraints and robot navigation tasks with images and raw Lidar scans as observations.
  arXiv  Detail & Related papers  (2023-03-07T18:29:15Z)
• Evaluating Model-free Reinforcement Learning toward Safety-critical Tasks [70.76757529955577]
  This paper revisits prior work in this scope from the perspective of state-wise safe RL. We propose Unrolling Safety Layer (USL), a joint method that combines safety optimization and safety projection. To facilitate further research in this area, we reproduce related algorithms in a unified pipeline and incorporate them into SafeRL-Kit.
  arXiv  Detail & Related papers  (2022-12-12T06:30:17Z)
• Near-Optimal Multi-Agent Learning for Safe Coverage Control [76.99020416197631]
  In multi-agent coverage control problems, agents navigate their environment to reach locations that maximize the coverage of some density. In this paper, we aim to efficiently learn the density to approximately solve the coverage problem while preserving the agents' safety. We give first of its kind results: near optimal coverage in finite time while provably guaranteeing safety.
  arXiv  Detail & Related papers  (2022-10-12T16:33:34Z)
• Exploration Policies for On-the-Fly Controller Synthesis: A Reinforcement Learning Approach [0.0]
  We propose a new method for obtaining unboundeds based on Reinforcement Learning (RL) Our agents learn from scratch in a highly observable partially RL task and outperform existing overall, in instances unseen during training.
  arXiv  Detail & Related papers  (2022-10-07T20:28:25Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• SAUTE RL: Almost Surely Safe Reinforcement Learning Using State Augmentation [63.25418599322092]
  Satisfying safety constraints almost surely (or with probability one) can be critical for deployment of Reinforcement Learning (RL) in real-life applications. We address the problem by introducing Safety Augmented Markov Decision Processes (MDPs) We show that Saute MDP allows to view Safe augmentation problem from a different perspective enabling new features.
  arXiv  Detail & Related papers  (2022-02-14T08:57:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.