# Multi-Task Optimization over Networks of Tasks

arXiv: https://arxiv.org/abs/2604.21991 · HTML: https://mlsanity.com/paper/2604.21991/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 58 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm](https://mlsanity.com/paper/1610.05729/) (2016)
- [Quality-Diversity Optimization: a novel branch of stochastic optimization](https://mlsanity.com/paper/2012.04322/) (2020)
- [Discovering the Elite Hypervolume by Leveraging Interspecies Correlation](https://mlsanity.com/paper/1804.03906/) (2018)
- [Quality Diversity for Multi-task Optimization](https://mlsanity.com/paper/2003.04407/) (2020)
- [Half a Dozen Real-World Applications of Evolutionary Multitasking, and More](https://mlsanity.com/paper/2109.13101/) (2021)
- [Evolutionary Multitask Optimization: a Methodological Overview, Challenges and Future Research Directions](https://mlsanity.com/paper/2102.02558/) (2021)
- [Meta-control of social learning strategies](https://mlsanity.com/paper/2106.10015/) (2021)
- [Multi-Task Multi-Behavior MAP-Elites](https://mlsanity.com/paper/2305.01264/) (2023)
- [Parametric-Task MAP-Elites](https://mlsanity.com/paper/2402.01275/) (2024)
- [Evolving generalist controllers to handle a wide range of morphological variations](https://mlsanity.com/paper/2309.10201/) (2023)

## Abstract (arXiv)

Multi-task optimization is a powerful approach for solving a large number of tasks in parallel. However, existing algorithms face distinct limitations: Population-based methods scale poorly and remain underexplored for large task sets. Approaches that do scale beyond a thousand tasks are mostly MAP-Elites variants and rely on a fixed, discretized archive that disregards the topology of the task space. We introduce MONET (Multi-Task Optimization over Networks of Tasks), a multi-task optimization algorithm that models the task space as a graph: tasks are nodes, and edges connect tasks in the task parameter space. This representation enables knowledge transfer between tasks and remains tractable for high-dimensional problems while exploiting the topology of the task space. MONET combines social learning, which generates candidates from neighboring nodes via crossover, with individual learning, which refines a node's own solution independently via mutation. We evaluate MONET on four domains (archery, arm, and cartpole with 5,000 tasks each; hexapod with 2,000 tasks) and show that it matches or exceeds the performance of existing MAP-Elites-based baselines across all four domains.