mlsanityData to 7 Oct 2026

Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning

arXiv 2502.19652 ↗First posted 27 Feb 2025cs.LG cs.AI cs.ROcited by 12

Not on the map. Why?

Abstract (arXiv)

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 algorithms within this framework, uncovering significant deficiencies in each and offering new insights.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 62 of its 97 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

62 of 97 references.

References · 62

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  4. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,366
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  6. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  7. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  8. 2017Deep Reinforcement Learning that Matterscited by 727
  9. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  10. 2020robosuite: A Modular Simulation Framework and Benchmark for Robot Learningcited by 484
  11. 2017Robust Adversarial Reinforcement Learningcited by 439
  12. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
38 more
  1. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 380
  2. 2020dm_control: Software and Tasks for Continuous Controlcited by 368
  3. 2016Benchmarking Deep Reinforcement Learning for Continuous Controlcited by 361
  4. 2017Adversarial Attacks on Neural Network Policiescited by 314
  5. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
  6. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  7. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  8. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  9. 2020The NetHack Learning Environmentcited by 196
  10. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 193
  11. 2020FACMAC: Factored Multi-Agent Centralised Policy Gradientscited by 178
  12. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 167
  13. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  14. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
  15. 2020CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guaranteecited by 128
  16. 2024THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulationcited by 128
  17. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 112
  18. 2024HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulationcited by 101
  19. 2022A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspectivecited by 100
  20. 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 95
  21. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 85
  22. 2018Benchmarking Reinforcement Learning Algorithms on Real-World Robotscited by 64
  23. 2018How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experimentscited by 56
  24. 2019Measuring the Reliability of Reinforcement Learning Algorithmscited by 49
  25. 2020Partial Policy Iteration for L1-Robust Markov Decision Processescited by 49
  26. 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 42
  27. 2019Distributionally Robust Reinforcement Learningcited by 40
  28. 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 40
  29. 2020Distributional Robustness and Regularization in Reinforcement Learningcited by 39
  30. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  31. 2023Robust Multi-Agent Reinforcement Learning with State Uncertaintycited by 35
  32. 2018Natural Environment Benchmarks for Reinforcement Learningcited by 32
  33. 2020Robustifying Reinforcement Learning Agents via Action Space Adversarial Trainingcited by 30
  34. 2021DACBench: A Benchmark Library for Dynamic Algorithm Configurationcited by 28
  35. 2023Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlationcited by 25
  36. 2023The Generalization Gap in Offline Reinforcement Learningcited by 25
  37. 2020Robust Finite-State Controllers for Uncertain POMDPscited by 23
  38. 2022CompoSuite: A Compositional Reinforcement Learning Benchmarkcited by 21

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 8; 2026: 4.

12 papers.

  1. 2025RobustVLA: Robustness-Aware Reinforcement Post-Training for Vision-Language-Action Modelscited by 16
  2. 2025Towards Agents That Know When They Don't Know: Uncertainty as a Control Signal for Structured Reasoningcited by 10
  3. 2025Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Dualitycited by 4
  4. 2025STORI: A Benchmark and Taxonomy for Stochastic Environmentscited by 2
  5. 2025Safe In-Context Reinforcement Learningcited by 2
  6. 2025RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigationcited by 1
  7. 2025Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learningcited by 1
  8. 2025Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Setscited by 0
  9. 2026CMR: Contractive Mapping Embeddings for Robust Humanoid Locomotion on Unstructured Terrainscited by 0
  10. 2026Synthetic Monitoring Environments for Reinforcement Learningcited by 0
  11. 2026A Unified Causal-Origin Taxonomy of Distributional Shifts in Reinforcement Learningcited by 0
  12. 2026Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPCcited by 0