mlsanityData to 14 Oct 2026

Replicable Reinforcement Learning

arXiv 2305.15284 ↗First posted 24 May 2023cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

The replicability crisis in the social, behavioral, and data sciences has led to the formulation of algorithm frameworks for replicability -- i.e., a requirement that an algorithm produce identical outputs (with high probability) when run on two different samples from the same underlying distribution. While still in its infancy, provably replicable algorithms have been developed for many fundamental tasks in machine learning and statistics, including statistical query learning, the heavy hitters problem, and distribution testing. In this work we initiate the study of replicable reinforcement learning, providing a provably replicable algorithm for parallel value iteration, and a provably replicable version of R-max in the episodic setting. These are the first formal replicability results for control problems, which present different challenges for replication than batch learning settings.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 24 of its 46 references that are in the map. First posted on arXiv 24 May 2023.

Builds on

24 of 46 references.

References · 24

  1. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  2. 2017Deep Reinforcement Learning that Matterscited by 754
  3. 2017Minimax Regret Bounds for Reinforcement Learningcited by 503
  4. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 322
  5. 2019Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Boundscited by 195
  6. 2020Reward-Free Exploration for Reinforcement Learningcited by 177
  7. 2015Sample Complexity of Episodic Fixed-Horizon Reinforcement Learningcited by 106
  8. 2019Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPscited by 105
  9. 2017Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Controlcited by 93
  10. 2021d3rlpy: An Offline Deep Reinforcement Learning Librarycited by 84
  11. 2021Sample Complexity of Robust Reinforcement Learning with a Generative Modelcited by 83
  12. 2020Adaptive Reward-Free Explorationcited by 77
12 more
  1. 2022Reproducibility in Learningcited by 44
  2. 2023Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalizationcited by 42
  3. 2016On Lower Bounds for Regret in Reinforcement Learningcited by 40
  4. 2019Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPscited by 40
  5. 2020Evaluating the Performance of Reinforcement Learning Algorithmscited by 36
  6. 2015Distributionally Robust Counterpart in Markov Decision Processescited by 33
  7. 2022Replicable Banditscited by 22
  8. 2022Reproducibility in Optimization: Theoretical Framework and Limitscited by 21
  9. 2022CompoSuite: A Compositional Reinforcement Learning Benchmarkcited by 21
  10. 2018Deterministic Implementations for Reproducibility in Deep Reinforcement Learningcited by 19
  11. 2023Statistical Indistinguishability of Learning Algorithmscited by 17
  12. 2019A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robotscited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 9; 2025: 5; 2026: 6.

21 papers.

Sort:

By area:

  1. 2023Replicability in Reinforcement Learningcited by 21
  2. 2024MAD-TD: Model-Augmented Data stabilizes High Update Ratio RLcited by 16
  3. 2024Replicable Learning of Large-Margin Halfspacescited by 12
  4. 2024Replicability in High Dimensional Statisticscited by 8
  5. 2024On the Computational Landscape of Replicable Learningcited by 7
  6. 2024Replicable Online Learningcited by 7
  7. 2025Replicable Reinforcement Learning with Linear Function Approximationcited by 7
  8. 2024Replicable Uniformity Testingcited by 4
  9. 2025Stability and List-Replicability for Agnostic Learnerscited by 4
  10. 2025Borsuk-Ulam and Replicable Learning of Large-Margin Halfspacescited by 4
  11. 2024Replicability is Asymptotically Free in Multi-armed Banditscited by 2
  12. 2024The Cost of Replicability in Active Learningcited by 2
9 more
  1. 2025Replicable Distribution Testingcited by 2
  2. 2025Simplicial covering dimension of extremal concept classescited by 2
  3. 2026Model Agreement via Anchoringcited by 1
  4. 2026Behavior-Consistent Deep Reinforcement Learningcited by 1
  5. 2026Tight list replicability bounds via a novel sphere covering theoremcited by 1
  6. 2026Sign-Rank, Index, and List Replicability: Connections and Separationscited by 1
  7. 2024Generalizability of experimental studiescited by 0
  8. 2026Computationally Efficient Replicable Learning of Parities and Applicationscited by 0
  9. 2026Replicable Bandits with UCB based Explorationcited by 0