Robust Gymnasium: A Unified Modular Benchmark For Robust Reinforcement Learning

Abstract

Driven by inherent uncertainty and the sim-to-real gap, robust reinforcement learning (RL) seeks to improve resilience against the complexity and variability in agent-environment sequential interactions. Despite the existence of a large number of RL benchmarks, there is a lack of standardized benchmarks for robust RL. Current robust RL policies often focus on a specific type of uncertainty and are evaluated in distinct, one-off environments. In this work, we introduce Robust-Gymnasium, a unified modular benchmark designed for robust RL that supports a wide variety of disruptions across all key RL components-agents' observed state and reward, agents' actions, and the environment. Offering over sixty diverse task environments spanning control and robotics, safe RL, and multi-agent RL, it provides an open-source and user-friendly tool for the community to assess current methods and foster the development of robust RL algorithms. In addition, we benchmark existing standard and robust RL al

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygu2025robust

Related papers

• Sample-efficient Robust Multi-agent Reinforcement Learning In The Face Of Environmental Uncertainty (2024)0.00
• Gymnasium: A Standard Interface For Reinforcement Learning Environments (2024)0.00
• Safe Reinforcement Learning With Dual Robustness (2023)8.60
• Combining Pessimism With Optimism For Robust And Efficient Model-based Deep Reinforcement Learning (2021)0.00
• Feasible Adversarial Robust Reinforcement Learning For Underspecified Environments (2022)0.00
• Robust Model-free Reinforcement Learning With Multi-objective Bayesian Optimization (2019)11.08
• Online Robust Reinforcement Learning With Model Uncertainty (2021)0.00
• Reliable Validation Of Reinforcement Learning Benchmarks (2022)0.00