# MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL

arXiv: https://arxiv.org/abs/2410.08896 · HTML: https://mlsanity.com/paper/2410.08896/

## Key facts

- Cited by 16 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 74 of its 98 references that are in the map.
- First posted on arXiv 11 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 74)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [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)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [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)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Temporal Difference Learning for Model Predictive Control](https://mlsanity.com/paper/2203.04955/) (2022)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Data-Efficient Reinforcement Learning with Self-Predictive Representations](https://mlsanity.com/paper/2007.05929/) (2020)
- [Randomized Ensembled Double Q-Learning: Learning Fast Without a Model](https://mlsanity.com/paper/2101.05982/) (2021)
- [The Primacy Bias in Deep Reinforcement Learning](https://mlsanity.com/paper/2205.07802/) (2022)
- [Revisiting Fundamentals of Experience Replay](https://mlsanity.com/paper/2007.06700/) (2020)
- [The Dormant Neuron Phenomenon in Deep Reinforcement Learning](https://mlsanity.com/paper/2302.12902/) (2023)
- [Understanding plasticity in neural networks](https://mlsanity.com/paper/2303.01486/) (2023)
- [Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion](https://mlsanity.com/paper/1807.01675/) (2018)
- [Bigger, Better, Faster: Human-level Atari with human-level efficiency](https://mlsanity.com/paper/2305.19452/) (2023)
- [Stop Regressing: Training Value Functions via Classification for Scalable Deep RL](https://mlsanity.com/paper/2403.03950/) (2024)
- [Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning](https://mlsanity.com/paper/2010.14498/) (2020)

## Built on by (most cited first, 16 of 16)

- [FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Control](https://mlsanity.com/paper/2505.22642/) (2025)
- [Hyperspherical Normalization for Scalable Deep Reinforcement Learning](https://mlsanity.com/paper/2502.15280/) (2025)
- [Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization](https://mlsanity.com/paper/2502.07523/) (2025)
- [Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents](https://mlsanity.com/paper/2510.13704/) (2025)
- [Relative Entropy Pathwise Policy Optimization](https://mlsanity.com/paper/2507.11019/) (2025)
- [Replicable Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2509.08660/) (2025)
- [Calibrated Value-Aware Model Learning with Probabilistic Environment Models](https://mlsanity.com/paper/2505.22772/) (2025)
- [Temporal Difference Learning with Constrained Initial Representations](https://mlsanity.com/paper/2602.11800/) (2026)
- [Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies](https://mlsanity.com/paper/2508.03194/) (2025)
- [Reward-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2603.05066/) (2026)
- [Debiased Model-based Representations for Sample-efficient Continuous Control](https://mlsanity.com/paper/2605.11711/) (2026)
- [Behavior-Consistent Deep Reinforcement Learning](https://mlsanity.com/paper/2605.21214/) (2026)
- [Iterative Compositional Data Generation for Robot Control](https://mlsanity.com/paper/2512.10891/) (2025)
- [R2R2: Robust Representation for Intensive Experience Reuse via Redundancy Reduction in Self-Predictive Learning](https://mlsanity.com/paper/2605.14026/) (2026)
- [Deconstructing Actor-Critic: A Large-scale Empirical Study of Design Components for Practitioners](https://mlsanity.com/paper/2607.13274/) (2026)
- [Rank Collapse Is Recoverable, Growing |Q| Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic](https://mlsanity.com/paper/2609.32819/) (2026)

## Abstract (arXiv)

Building deep reinforcement learning (RL) agents that find a good policy with few samples has proven notoriously challenging. To achieve sample efficiency, recent work has explored updating neural networks with large numbers of gradient steps for every new sample. While such high update-to-data (UTD) ratios have shown strong empirical performance, they also introduce instability to the training process. Previous approaches need to rely on periodic neural network parameter resets to address this instability, but restarting the training process is infeasible in many real-world applications and requires tuning the resetting interval. In this paper, we focus on one of the core difficulties of stable training with limited samples: the inability of learned value functions to generalize to unobserved on-policy actions. We mitigate this issue directly by augmenting the off-policy RL training process with a small amount of data generated from a learned world model. Our method, Model-Augmented Data for TD Learning (MAD-TD), uses small amounts of generated data to stabilize high UTD training and achieve competitive performance on the most challenging tasks in the DeepMind control suite. Our experiments further highlight the importance of employing a good model to generate data, MAD-TD's ability to combat value overestimation, and its practical stability gains for continued learning.