# Understanding and Mitigating the Limitations of Prioritized Experience Replay

arXiv: https://arxiv.org/abs/2007.09569 · HTML: https://mlsanity.com/paper/2007.09569/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2020.

## Built on by (most cited first, 17 of 17)

- [Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization](https://mlsanity.com/paper/2301.07784/) (2023)
- [Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning](https://mlsanity.com/paper/2509.22601/) (2025)
- [Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation](https://mlsanity.com/paper/2205.10868/) (2022)
- [Selective experience replay compression using coresets for lifelong deep reinforcement learning in medical imaging](https://mlsanity.com/paper/2302.11510/) (2023)
- [Uncertainty Prioritized Experience Replay](https://mlsanity.com/paper/2506.09270/) (2025)
- [Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning](https://mlsanity.com/paper/2306.15503/) (2023)
- [LiRA: Light-Robust Adversary for Model-based Reinforcement Learning in Real World](https://mlsanity.com/paper/2409.19617/) (2024)
- [ETGL-DDPG: A Deep Deterministic Policy Gradient Algorithm for Sparse Reward Continuous Control](https://mlsanity.com/paper/2410.05225/) (2024)
- [Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning](https://mlsanity.com/paper/2505.05701/) (2025)
- [Debiased Model-based Representations for Sample-efficient Continuous Control](https://mlsanity.com/paper/2605.11711/) (2026)
- [Discerning Temporal Difference Learning](https://mlsanity.com/paper/2310.08091/) (2023)
- [Variance Reduction Based Experience Replay for Policy Optimization](https://mlsanity.com/paper/2602.05379/) (2026)
- [WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation](https://mlsanity.com/paper/2603.17301/) (2026)
- [A hierarchical spatial-aware algorithm with efficient reinforcement learning for human-robot task planning and allocation in production](https://mlsanity.com/paper/2604.12669/) (2026)
- [Integrating Novelty and Surprise for Experience Prioritization and Exploration in Image-Based Reinforcement Learning](https://mlsanity.com/paper/2608.17373/) (2026)
- [Uncertainty-Driven Replay Memory for Reinforcement Learning](https://mlsanity.com/paper/2608.29860/) (2026)
- [Correcting Within-Group Self-Selection Bias in Prioritized Replay](https://mlsanity.com/paper/2609.25297/) (2026)

## Abstract (arXiv)

Prioritized Experience Replay (ER) has been empirically shown to improve sample efficiency across many domains and attracted great attention; however, there is little theoretical understanding of why such prioritized sampling helps and its limitations. In this work, we take a deep look at the prioritized ER. In a supervised learning setting, we show the equivalence between the error-based prioritized sampling method for mean squared error and uniform sampling for cubic power loss. We then provide theoretical insight into why it improves convergence rate upon uniform sampling during early learning. Based on the insight, we further point out two limitations of the prioritized ER method: 1) outdated priorities and 2) insufficient coverage of the sample space. To mitigate the limitations, we propose our model-based stochastic gradient Langevin dynamics sampling method. We show that our method does provide states distributed close to an ideal prioritized sampling distribution estimated by the brute-force method, which does not suffer from the two limitations. We conduct experiments on both discrete and continuous control problems to show our approach's efficacy and examine the practical implication of our method in an autonomous driving application.