# Learning to Transfer for Evolutionary Multitasking

arXiv: https://arxiv.org/abs/2406.14359 · HTML: https://mlsanity.com/paper/2406.14359/

## Key facts

- Cited by 6 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 8 of its 32 references that are in the map.
- First posted on arXiv 20 Jun 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, 8 of 8)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting](https://mlsanity.com/paper/1603.08785/) (2016)
- [Evolution-Guided Policy Gradient in Reinforcement Learning](https://mlsanity.com/paper/1805.07917/) (2018)
- [MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning](https://mlsanity.com/paper/2310.08252/) (2023)
- [Learning adaptive differential evolution algorithm from optimization experiences by policy gradient](https://mlsanity.com/paper/2102.03572/) (2021)
- [Meta-Surrogate Benchmarking for Hyperparameter Optimization](https://mlsanity.com/paper/1905.12982/) (2019)
- [Evolutionary Multitasking for Single-objective Continuous Optimization: Benchmark Problems, Performance Metric, and Baseline Results](https://mlsanity.com/paper/1706.03470/) (2017)

## Built on by (most cited first, 6 of 6)

- [Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization](https://mlsanity.com/paper/2411.00625/) (2024)
- [Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning](https://mlsanity.com/paper/2503.18061/) (2025)
- [MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization](https://mlsanity.com/paper/2505.17745/) (2025)
- [Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking](https://mlsanity.com/paper/2511.15199/) (2025)
- [SMILE: A Super-resolution Guided Multi-task Learning Method for Hyperspectral Unmixing](https://mlsanity.com/paper/2509.11093/) (2025)
- [Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero](https://mlsanity.com/paper/2609.35328/) (2026)

## Abstract (arXiv)

Evolutionary multitasking (EMT) is an emerging approach for solving multitask optimization problems (MTOPs) and has garnered considerable research interest. The implicit EMT is a significant research branch that utilizes evolution operators to enable knowledge transfer (KT) between tasks. However, current approaches in implicit EMT face challenges in adaptability, due to the use of a limited number of evolution operators and insufficient utilization of evolutionary states for performing KT. This results in suboptimal exploitation of implicit KT's potential to tackle a variety of MTOPs. To overcome these limitations, we propose a novel Learning to Transfer (L2T) framework to automatically discover efficient KT policies for the MTOPs at hand. Our framework conceptualizes the KT process as a learning agent's sequence of strategic decisions within the EMT process. We propose an action formulation for deciding when and how to transfer, a state representation with informative features of evolution states, a reward formulation concerning convergence and transfer efficiency gain, and the environment for the agent to interact with MTOPs. We employ an actor-critic network structure for the agent and learn it via proximal policy optimization. This learned agent can be integrated with various evolutionary algorithms, enhancing their ability to address a range of new MTOPs. Comprehensive empirical studies on both synthetic and real-world MTOPs, encompassing diverse inter-task relationships, function classes, and task distributions are conducted to validate the proposed L2T framework. The results show a marked improvement in the adaptability and performance of implicit EMT when solving a wide spectrum of unseen MTOPs.