# Multi-Task Multi-Behavior MAP-Elites

arXiv: https://arxiv.org/abs/2305.01264 · HTML: https://mlsanity.com/paper/2305.01264/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2023.

## Built on by (most cited first, 5 of 5)

- [Quality Diversity under Sparse Reward and Sparse Interaction: Application to Grasping in Robotics](https://mlsanity.com/paper/2308.05483/) (2023)
- [Parametric-Task MAP-Elites](https://mlsanity.com/paper/2402.01275/) (2024)
- [Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning](https://mlsanity.com/paper/2604.15414/) (2026)
- [Exploring Knowledge Transfer in Evolutionary Many-task Optimization: A Complex Network Perspective](https://mlsanity.com/paper/2407.08918/) (2024)
- [Multi-Task Optimization over Networks of Tasks](https://mlsanity.com/paper/2604.21991/) (2026)

## Abstract (arXiv)

We propose Multi-Task Multi-Behavior MAP-Elites, a variant of MAP-Elites that finds a large number of high-quality solutions for a large set of tasks (optimization problems from a given family). It combines the original MAP-Elites for the search for diversity and Multi-Task MAP-Elites for leveraging similarity between tasks. It performs better than three baselines on a humanoid fault-recovery set of tasks, solving more tasks and finding twice as many solutions per solved task.