# Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learning

arXiv: https://arxiv.org/abs/2602.09813 · HTML: https://mlsanity.com/paper/2602.09813/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in On-policy and self-distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/)

## Builds on (most cited first, 26 of 26)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning](https://mlsanity.com/paper/2208.06193/) (2022)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [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)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [Learning Vision-Based Bipedal Locomotion for Challenging Terrain](https://mlsanity.com/paper/2309.14594/) (2023)
- [Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning](https://mlsanity.com/paper/2407.15815/) (2024)
- [Deep Surrogate Assisted Generation of Environments](https://mlsanity.com/paper/2206.04199/) (2022)
- [A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models](https://mlsanity.com/paper/2502.13187/) (2025)
- [Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft](https://mlsanity.com/paper/2106.14876/) (2021)
- [CLUTR: Curriculum Learning via Unsupervised Task Representation Learning](https://mlsanity.com/paper/2210.10243/) (2022)
- [DRED: Zero-Shot Transfer in Reinforcement Learning via Data-Regularised Environment Design](https://mlsanity.com/paper/2402.03479/) (2024)
- [Transferable Curricula through Difficulty Conditioned Generators](https://mlsanity.com/paper/2306.13028/) (2023)
- [Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity](https://mlsanity.com/paper/2411.04466/) (2024)

## Abstract (arXiv)

Unsupervised Environment Design (UED) has emerged as a promising approach to developing general-purpose agents through automated curriculum generation. Popular UED methods focus on Open-Endedness, where teacher algorithms rely on stochastic processes for infinite generation of useful environments. This assumption becomes impractical in resource-constrained scenarios where teacher-student interaction opportunities are limited. To address this challenge, we introduce a hierarchical Markov Decision Process (MDP) framework for environment design. Our framework features a teacher agent that leverages student policy representations derived from discovered evaluation environments, enabling it to generate training environments based on the student's capabilities. To improve efficiency, we incorporate a generative model that augments the teacher's training dataset with synthetic data, reducing the need for teacher-student interactions. In experiments across several domains, we show that our method outperforms baseline approaches while requiring fewer teacher-student interactions in a single episode. The results suggest the applicability of our approach in settings where training opportunities are limited.