# DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design

arXiv: https://arxiv.org/abs/2402.03479 · HTML: https://mlsanity.com/paper/2402.03479/

## Key facts

- Cited by 11 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 33 of its 47 references that are in the map.
- First posted on arXiv 5 Feb 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 33)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Learning Quadrupedal Locomotion over Challenging Terrain](https://mlsanity.com/paper/2010.11251/) (2020)
- [Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels](https://mlsanity.com/paper/2004.13649/) (2020)
- [Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning](https://mlsanity.com/paper/2109.11978/) (2021)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Quantifying Generalization in Reinforcement Learning](https://mlsanity.com/paper/1812.02341/) (2018)
- [Information-theoretic analysis of generalization capability of learning algorithms](https://mlsanity.com/paper/1705.07809/) (2017)
- [Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design](https://mlsanity.com/paper/2012.02096/) (2020)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [A Study on Overfitting in Deep Reinforcement Learning](https://mlsanity.com/paper/1804.06893/) (2018)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Assessing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1810.12282/) (2018)
- [Replay-Guided Adversarial Environment Design](https://mlsanity.com/paper/2110.02439/) (2021)
- [Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability](https://mlsanity.com/paper/2107.06277/) (2021)
- [Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck](https://mlsanity.com/paper/1910.12911/) (2019)
- [Automatic Curriculum Learning through Value Disagreement](https://mlsanity.com/paper/2006.09641/) (2020)
- [OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets](https://mlsanity.com/paper/2007.12868/) (2020)
- [MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning](https://mlsanity.com/paper/2310.08252/) (2023)
- [Conditional Mutual Information for Disentangled Representations in Reinforcement Learning](https://mlsanity.com/paper/2305.14133/) (2023)
- [Learning to Optimize in Swarms](https://mlsanity.com/paper/1911.03787/) (2019)

## Built on by (most cited first, 11 of 11)

- [Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks](https://mlsanity.com/paper/2410.23208/) (2024)
- [No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery](https://mlsanity.com/paper/2408.15099/) (2024)
- [Beyond Pixel Histories: World Models with Persistent 3D State](https://mlsanity.com/paper/2603.03482/) (2026)
- [Adversarial Environment Design via Regret-Guided Diffusion Models](https://mlsanity.com/paper/2410.19715/) (2024)
- [An Optimisation Framework for Unsupervised Environment Design](https://mlsanity.com/paper/2505.20659/) (2025)
- [Multi-view Disentanglement for Reinforcement Learning with Multiple Cameras](https://mlsanity.com/paper/2404.14064/) (2024)
- [Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning](https://mlsanity.com/paper/2503.06343/) (2025)
- [Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments](https://mlsanity.com/paper/2407.03969/) (2024)
- [Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs](https://mlsanity.com/paper/2511.12706/) (2025)
- [Skill-aware Mutual Information Optimisation for Generalisation in Reinforcement Learning](https://mlsanity.com/paper/2406.04815/) (2024)
- [Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learning](https://mlsanity.com/paper/2602.09813/) (2026)

## Abstract (arXiv)

Autonomous agents trained using deep reinforcement learning (RL) often lack the ability to successfully generalise to new environments, even when these environments share characteristics with the ones they have encountered during training. In this work, we investigate how the sampling of individual environment instances, or levels, affects the zero-shot generalisation (ZSG) ability of RL agents. We discover that, for deep actor-critic architectures sharing their base layers, prioritising levels according to their value loss minimises the mutual information between the agent's internal representation and the set of training levels in the generated training data. This provides a novel theoretical justification for the regularisation achieved by certain adaptive sampling strategies. We then turn our attention to unsupervised environment design (UED) methods, which assume control over level generation. We find that existing UED methods can significantly shift the training distribution, which translates to low ZSG performance. To prevent both overfitting and distributional shift, we introduce data-regularised environment design (DRED). DRED generates levels using a generative model trained to approximate the ground truth distribution of an initial set of level parameters. Through its grounding, DRED achieves significant improvements in ZSG over adaptive level sampling strategies and UED methods. Our code and experimental data are available at https://github.com/uoe-agents/dred.