# When Does Non-Uniform Replay Matter in Reinforcement Learning?

arXiv: https://arxiv.org/abs/2605.10236 · HTML: https://mlsanity.com/paper/2605.10236/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 27 of 27)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Distributed Distributional Deterministic Policy Gradients](https://mlsanity.com/paper/1804.08617/) (2018)
- [HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation](https://mlsanity.com/paper/2403.10506/) (2024)
- [Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous control](https://mlsanity.com/paper/2405.16158/) (2024)
- [CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity](https://mlsanity.com/paper/1902.05605/) (2019)
- [A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning](https://mlsanity.com/paper/2208.07860/) (2022)
- [MyoSuite -- A contact-rich simulation suite for musculoskeletal motor control](https://mlsanity.com/paper/2205.13600/) (2022)
- [SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning](https://mlsanity.com/paper/2410.09754/) (2024)
- [FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control](https://mlsanity.com/paper/2505.22642/) (2025)
- [Towards General-Purpose Model-Free Reinforcement Learning](https://mlsanity.com/paper/2501.16142/) (2025)
- [Hyperspherical Normalization for Scalable Deep Reinforcement Learning](https://mlsanity.com/paper/2502.15280/) (2025)
- [Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners](https://mlsanity.com/paper/2505.23150/) (2025)
- [Boosting Soft Actor-Critic: Emphasizing Recent Experience without Forgetting the Past](https://mlsanity.com/paper/1906.04009/) (2019)
- [XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learning](https://mlsanity.com/paper/2509.25174/) (2025)
- [Learning Sim-to-Real Humanoid Locomotion in 15 Minutes](https://mlsanity.com/paper/2512.01996/) (2025)
- [Value-Based Deep RL Scales Predictably](https://mlsanity.com/paper/2502.04327/) (2025)
- [Compute-Optimal Scaling for Value-Based Deep RL](https://mlsanity.com/paper/2508.14881/) (2025)
- [Reliability-Adjusted Prioritized Experience Replay](https://mlsanity.com/paper/2506.18482/) (2025)
- [What Matters for Simulation to Online Reinforcement Learning on Real Robots](https://mlsanity.com/paper/2602.20220/) (2026)

## Abstract (arXiv)

Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong baseline. Across diverse RL settings, we show that the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. Our main contribution is clarifying when non-uniform replay is beneficial and providing practical guidance for replay design in modern off-policy RL. Namely, we find that non-uniform replay is most beneficial when replay volume is low, and that high-entropy sampling is important even at comparable expected recency. Motivated by these findings, we adopt a simple Truncated Geometric replay that biases sampling toward recent experience while preserving high entropy and incurring negligible computational overhead. Across large-scale parallel simulation, single-task, and multi-task settings, including three modern algorithms evaluated on five RL benchmark suites, this replay sampling strategy improves sample efficiency in low-volume regimes while remaining competitive when replay volume is high.