# Prioritized Generative Replay

arXiv: https://arxiv.org/abs/2410.18082 · HTML: https://mlsanity.com/paper/2410.18082/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 53 of its 66 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## 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, 30 of 53)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019)
- [Unifying Count-Based Exploration and Intrinsic Motivation](https://mlsanity.com/paper/1606.01868/) (2016)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Deep Exploration via Bootstrapped DQN](https://mlsanity.com/paper/1602.04621/) (2016)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning](https://mlsanity.com/paper/2208.04202/) (2022)
- [Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning](https://mlsanity.com/paper/2107.09645/) (2021)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [Noisy Networks for Exploration](https://mlsanity.com/paper/1706.10295/) (2017)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Mastering Atari Games with Limited Data](https://mlsanity.com/paper/2111.00210/) (2021)

## Built on by (most cited first, 13 of 13)

- [State-Covering Trajectory Stitching for Diffusion Planners](https://mlsanity.com/paper/2506.00895/) (2025)
- [Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning](https://mlsanity.com/paper/2506.00867/) (2025)
- [Exploratory Diffusion Model for Unsupervised Reinforcement Learning](https://mlsanity.com/paper/2502.07279/) (2025)
- [BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning](https://mlsanity.com/paper/2506.05762/) (2025)
- [Off-policy Reinforcement Learning with Model-based Exploration Augmentation](https://mlsanity.com/paper/2510.25529/) (2025)
- [Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning](https://mlsanity.com/paper/2505.01822/) (2025)
- [Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies](https://mlsanity.com/paper/2508.03194/) (2025)
- [Replay-buffer engineering for noise-aware quantum circuit optimization](https://mlsanity.com/paper/2604.21863/) (2026)
- [Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution](https://mlsanity.com/paper/2606.22314/) (2026)
- [Noise-Tolerant Coreset-Based Class Incremental Continual Learning](https://mlsanity.com/paper/2504.16763/) (2025)
- [Decision Flow Policy Optimization](https://mlsanity.com/paper/2505.20350/) (2025)
- [Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning](https://mlsanity.com/paper/2607.25123/) (2026)
- [Generative Replay Mitigates Sample Starvation in Quantum Architecture Search](https://mlsanity.com/paper/2609.11248/) (2026)

## Abstract (arXiv)

Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to learning. While prioritization of more useful samples is helpful, this strategy can also lead to overfitting, as useful samples are likely to be more rare. In this work, we instead propose a prioritized, parametric version of an agent's memory, using generative models to capture online experience. This paradigm enables (1) densification of past experience, with new generations that benefit from the generative model's generalization capacity and (2) guidance via a family of "relevance functions" that push these generations towards more useful parts of an agent's acquired history. We show this recipe can be instantiated using conditional diffusion models and simple relevance functions such as curiosity- or value-based metrics. Our approach consistently improves performance and sample efficiency in both state- and pixel-based domains. We expose the mechanisms underlying these gains, showing how guidance promotes diversity in our generated transitions and reduces overfitting. We also showcase how our approach can train policies with even higher update-to-data ratios than before, opening up avenues to better scale online RL agents.