# Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversity

arXiv: https://arxiv.org/abs/2411.04466 · HTML: https://mlsanity.com/paper/2411.04466/

## Key facts

- Cited by 3 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 34 of its 45 references that are in the map.
- First posted on arXiv 7 Nov 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 34)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables](https://mlsanity.com/paper/1903.08254/) (2019)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design](https://mlsanity.com/paper/2012.02096/) (2020)
- [VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning](https://mlsanity.com/paper/1910.08348/) (2019)
- [Prioritized Level Replay](https://mlsanity.com/paper/2010.03934/) (2020)
- [Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions](https://mlsanity.com/paper/1901.01753/) (2019)
- [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)
- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [Replay-Guided Adversarial Environment Design](https://mlsanity.com/paper/2110.02439/) (2021)
- [A Tutorial on Meta-Reinforcement Learning](https://mlsanity.com/paper/2301.08028/) (2023)
- [Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions](https://mlsanity.com/paper/2003.08536/) (2020)
- [PCGRL: Procedural Content Generation via Reinforcement Learning](https://mlsanity.com/paper/2001.09212/) (2020)
- [Scenic: A Language for Scenario Specification and Scene Generation](https://mlsanity.com/paper/1809.09310/) (2018)
- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [Procedural Content Generation through Quality Diversity](https://mlsanity.com/paper/1907.04053/) (2019)
- [Transformers are Meta-Reinforcement Learners](https://mlsanity.com/paper/2206.06614/) (2022)
- [AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents](https://mlsanity.com/paper/2310.09971/) (2023)
- [Deep Surrogate Assisted Generation of Environments](https://mlsanity.com/paper/2206.04199/) (2022)
- [On the Importance of Environments in Human-Robot Coordination](https://mlsanity.com/paper/2106.10853/) (2021)
- [Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents](https://mlsanity.com/paper/2102.02926/) (2021)
- [Unsupervised Behaviour Discovery with Quality-Diversity Optimisation](https://mlsanity.com/paper/2106.05648/) (2021)
- [pyribs: A Bare-Bones Python Library for Quality Diversity Optimization](https://mlsanity.com/paper/2303.00191/) (2023)
- [Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning](https://mlsanity.com/paper/2010.01062/) (2020)
- [A Quality Diversity Approach to Automatically Generating Human-Robot Interaction Scenarios in Shared Autonomy](https://mlsanity.com/paper/2012.04283/) (2020)

## Built on by (most cited first, 3 of 3)

- [TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design](https://mlsanity.com/paper/2506.19997/) (2025)
- [Active Curriculum Refinement for Reinforcement Learning](https://mlsanity.com/paper/2608.26469/) (2026)
- [Efficient Unsupervised Environment Design through Hierarchical Policy Representation Learning](https://mlsanity.com/paper/2602.09813/) (2026)

## Abstract (arXiv)

The wider application of end-to-end learning methods to embodied decision-making domains remains bottlenecked by their reliance on a superabundance of training data representative of the target domain. Meta-reinforcement learning (meta-RL) approaches abandon the aim of zero-shot generalization--the goal of standard reinforcement learning (RL)--in favor of few-shot adaptation, and thus hold promise for bridging larger generalization gaps. While learning this meta-level adaptive behavior still requires substantial data, efficient environment simulators approaching real-world complexity are growing in prevalence. Even so, hand-designing sufficiently diverse and numerous simulated training tasks for these complex domains is prohibitively labor-intensive. Domain randomization (DR) and procedural generation (PG), offered as solutions to this problem, require simulators to possess carefully-defined parameters which directly translate to meaningful task diversity--a similarly prohibitive assumption. In this work, we present DIVA, an evolutionary approach for generating diverse training tasks in such complex, open-ended simulators. Like unsupervised environment design (UED) methods, DIVA can be applied to arbitrary parameterizations, but can additionally incorporate realistically-available domain knowledge--thus inheriting the flexibility and generality of UED, and the supervised structure embedded in well-designed simulators exploited by DR and PG. Our empirical results showcase DIVA's unique ability to overcome complex parameterizations and successfully train adaptive agent behavior, far outperforming competitive baselines from prior literature. These findings highlight the potential of such semi-supervised environment design (SSED) approaches, of which DIVA is the first humble constituent, to enable training in realistic simulated domains, and produce more robust and capable adaptive agents.