mlsanityData to 7 Oct 2026

Evaluating the Performance of Reinforcement Learning Algorithms

arXiv 2006.16958 ↗First posted 30 Jun 2020cs.LG stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results are often inconsistent and difficult to replicate. In this work, we argue that the inconsistency of performance stems from the use of flawed evaluation metrics. Taking a step towards ensuring that reported results are consistent, we propose a new comprehensive evaluation methodology for reinforcement learning algorithms that produces reliable measurements of performance both on a single environment and when aggregated across environments. We demonstrate this method by evaluating a broad class of reinforcement learning algorithms on standard benchmark tasks.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 7; 2023: 3; 2024: 4; 2025: 10; 2026: 4.

35 papers.

Sort:

By area:

  1. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  2. 2022Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimizationcited by 96
  3. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 89
  4. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  5. 2023Empirical Design in Reinforcement Learningcited by 54
  6. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 48
  7. 2021Batch size-invariance for policy optimizationcited by 33
  8. 2021Evaluating the Robustness of Off-Policy Evaluationcited by 32
  9. 2022How stable are Transferability Metrics evaluations?cited by 30
  10. 2021Is High Variance Unavoidable in RL? A Case Study in Continuous Controlcited by 26
  11. 2023Replicable Reinforcement Learningcited by 21
  12. 2021RLOps: Development Life-cycle of Reinforcement Learning Aided Open RANcited by 15
23 more
  1. 2024Position: Benchmarking is Limited in Reinforcement Learning Researchcited by 15
  2. 2024A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learningcited by 15
  3. 2025Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewardscited by 11
  4. 2022The Impact of Task Underspecification in Evaluating Deep Reinforcement Learningcited by 10
  5. 2025Benchmarking Quantum Reinforcement Learningcited by 9
  6. 2025Reinforcement Learning for Large Model: A Surveycited by 8
  7. 2022Robust Losses for Learning Value Functionscited by 7
  8. 2025Relative Entropy Pathwise Policy Optimizationcited by 6
  9. 2021A Distance-based Anomaly Detection Framework for Deep Reinforcement Learningcited by 5
  10. 2023PRUDEX-Compass: Towards Systematic Evaluation of Reinforcement Learning in Financial Marketscited by 5
  11. 2024Assessing the Impact of Distribution Shift on Reinforcement Learning Performancecited by 4
  12. 2021Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precisioncited by 3
  13. 2024The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learningcited by 2
  14. 2022Addressing the issue of stochastic environments and local decision-making in multi-objective reinforcement learningcited by 1
  15. 2025Learning more with the same effort: how randomization improves the robustness of a robotic deep reinforcement learning agentcited by 1
  16. 2025On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmarkcited by 1
  17. 2025Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative Studycited by 0
  18. 2025Domain-driven Metrics for Reinforcement Learning: A Case Study on Epidemic Control using Agent-based Simulationcited by 0
  19. 2025Best Practices For Empirical Meta-Algorithmic Research: Guidelines from the COSEAL Research Networkcited by 0
  20. 2026Piece of CAKE: Adaptive Execution Engines via Microsecond-Scale Learningcited by 0
  21. 2026Policy Optimality Measurement for Multi-Vehicle Decision-Making: From Extrinsic Indicators to Intrinsic Qualitycited by 0
  22. 2026What Does a ProcGen Generalization Gap Measure? Action Rules, Residual Entropy, and the Missing Random Floorcited by 0
  23. 2026Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RLcited by 0