[!IMPORTANT] Official companion repository for Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms.
This repository helps readers enter the ERL field faster, reproduce representative methods, navigate the survey taxonomy, and track new papers and code. It currently indexes 270 canonical algorithm works and curates 86 independently reviewed Chinese and English guide mappings across 80 unique URLs, covering 54 works.

---

Overview

_{Reproducible count policy (30 Aug 2026): one canonical work equals one unique paper record, regardless of aliases, variants, or cross-listings. The 270 total excludes tooling/benchmarks, field overviews, and the independent watchlist. Code coverage counts canonical works with an exact author/official or explicitly labeled community implementation.}

[!IMPORTANT] Which survey version should you use? Cite the IEEE version of record, read arXiv v5 for the latest paper content, and use this repository for code and ongoing updates. See the exact differences ↓

Choose a direction

Quick paths

Need reproducible baselines? Start from the code-first list and frameworks.
Need an explanation first? Start from the integrated bilingual reading-guide overview, then open the full work-by-work guide when you need a specific method.
Tracking the newest work? Go to recent and emerging directions.

[!NOTE] Code labels: repository links are author-maintained unless explicitly marked as a community implementation. Not found means no verified public implementation was located. Some methods are intentionally cross-listed when one mechanism contributes to multiple branches.

Changelog

• 30 Aug 2026 — completed a multi-scope coverage adjudication: added 120 canonical works, expanded the collection to 270 papers and 80 verified code artifacts, corrected QD-PG metadata, and retained 14 independently tracked boundary items in a non-counting watchlist.
• 29 Aug 2026 — refined the bilingual reading guide to 86 verified work-link mappings across 54 works after a stricter mechanism-depth audit removed mismatched and installation-only references.
• 28 Aug 2026 — synchronized the collection with arXiv v5; added Reward Design, Dynamic Operator Selection, missing QD methods, recent 2024–2026 work, verified code repositories, frameworks, and updated taxonomy figures.
• 26 Jul 2024 — the survey was accepted by IEEE Transactions on Evolutionary Computation.

Full section index

• Overview
• Bilingual reading guides
• Taxonomy
• Survey versions
• Code-first reading list
• EA-assisted Optimization of RL
  • EA-assisted Parameter Search
  • EA-assisted Action Selection
  • Hyperparameter Optimization
  • Algorithm and Update-rule Discovery
  • Other EA-assisted RL methods
• RL-assisted Optimization of EA
  • Population Initialization
  • Population Evaluation
  • Variation Operator
  • Quality-Diversity
  • Dynamic Operator Selection
  • Dynamic Algorithm Configuration
  • Dynamic Resource Allocation
  • Other RL-assisted EA methods
• Synergistic Optimization of EA and RL
  • Single-Agent Optimization
  • Adaptive, Staged, or Stabilized Coupling
  • Representation and Search Decomposition
  • Multi-Agent Optimization
  • Reward Design
  • Morphological Evolution
  • Interpretable AI
  • Learning Classifier Systems
• Frameworks, benchmarks, and tooling
• Recent and emerging directions
• Related surveys
• Contributing
• Citation

Bilingual reading guides

The reading guide is integrated into this repository as a second layer over the survey taxonomy: use the compact paths below to enter a direction quickly, then open the complete work-by-work guide for all reviewed resources.

Core marks substantial, work-specific explanations. Extended marks concise but mechanism-bearing overview sections, project documentation, thesis chapters, posters, or talk slides. Installation-only repositories, abstract restatements, and references that merely mention a method are excluded.

Guide coverage and mapping counts are deduplicated by canonical paper/work URL, language, guide URL, and Core/Extended label; aliases and cross-lists do not add mappings.

Browse the complete bilingual guide →

Taxonomy

Survey v5 organizes ERL into three major directions and sixteen research branches. The maintained repository uses twenty-one branches after adding five evidence-backed extensions: algorithm/update-rule discovery, quality-diversity, dynamic resource allocation, adaptive/staged/stabilized coupling, and representation/search decomposition.

_{Figure 1. Taxonomy of evolutionary reinforcement learning in survey v5.}

[!NOTE] Survey v5 Table V and the body text additionally include LERO under Reward Design and discuss XCSRG alongside XCSG. The detailed tables below follow the more complete body and tabular taxonomy.

_{Figure 2. Four integration patterns connecting EA and RL across solution and decomposed problem spaces.}

Survey versions

Difference at a glance: IEEE = archival citation · arXiv v5 = latest paper content · GitHub = maintained implementation index

The repository includes code availability, tooling, and newer work that should not be treated as part of the archival IEEE article.

Paper: Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms — Pengyi Li, Jianye Hao, Hongyao Tang, Xian Fu, Yan Zheng, and Ke Tang.

Code-first reading list

The following papers have public implementations verified against the paper, project page, or authors' repositories and are useful starting points. Community reimplementations are kept out of this short list and labeled explicitly in the full taxonomy.

Verified code-first collection (31 entries)

Direction	Method	Paper	Code	Guide
EA-assisted RL	SAC-CEPO	Soft Actor-Critic with Cross-Entropy Policy Optimization	wcgcyx/SAC-CEPO	Not found
EA-assisted RL	GRAC	GRAC: Self-Guided and Self-Regularized Actor-Critic	stanford-iprl-lab/GRAC	EN · Extended
EA-assisted RL	OMAR	Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification	ling-pan/OMAR	Not found
EA-assisted RL	SEARL	Sample-Efficient Automated Deep Reinforcement Learning	automl/SEARL	EN · Extended
EA-assisted RL	Evolving RL Algorithms	Evolving Reinforcement Learning Algorithms	google/brain_autorl	EN 1 · Core EN 2 · Core
EA-assisted RL	Go-Explore	Go-Explore: a New Approach for Hard-Exploration Problems	uber-research/go-explore	中文 1 · Core 中文 2 · Core EN 1 · Core EN 2 · Extended
EA-assisted RL	ROMANCE	Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers	zzq-bot/ROMANCE	Not found
EA-assisted RL	EvIL	Evolution Strategies for Generalisable Imitation Learning	SilviaSapora/evil	EN · Extended
RL-assisted EA	DeepACO	DeepACO: Neural-Enhanced Ant Systems for Combinatorial Optimization	henry-yeh/DeepACO	中文 1 · Core 中文 2 · Core EN · Extended
RL-assisted EA	CEM-RL	Combining Evolutionary and Gradient-Based Methods for Policy Search	apourchot/CEM-RL	中文 · Extended EN · Extended
RL-assisted EA	PGA-ME	Policy Gradient Assisted MAP-Elites	ollebompa/PGA-MAP-Elites	EN · Extended
RL-assisted EA	CMA-MEGA	Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning	icaros-usc/dqd-rl	EN 1 · Extended EN 2 · Extended
RL-assisted EA	CCQD	Sample-Efficient Quality-Diversity by Cooperative Coevolution	lamda-bbo/CCQD	Not found
RL-assisted EA	RefQD	Quality-Diversity with Limited Resources	lamda-bbo/RefQD	EN · Extended
RL-assisted EA	Wuji	Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement Learning	NeteaseFuxiRL/wuji	中文 · Core
Synergistic	ERL	Evolution-Guided Policy Gradient in Reinforcement Learning	ShawK91/Evolutionary-Reinforcement-Learning	EN 1 · Extended EN 2 · Extended
Synergistic	CERL	Collaborative Evolutionary Reinforcement Learning	intel/cerl	EN · Core
Synergistic	PDERL	Proximal Distilled Evolutionary Reinforcement Learning	crisbodnar/pderl	中文 · Extended
Synergistic	ERL-Re2	ERL-Re^2: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation	yeshenpy/ERL-Re2	中文 · Core EN · Extended
Synergistic	VEB-RL	Value-Evolutionary-Based Reinforcement Learning	yeshenpy/VEB-RL	中文 · Core EN · Extended
Synergistic	EvoRainbow	EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search	yeshenpy/EvoRainbow	中文 · Core EN · Extended
Synergistic	RACE	RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution	yeshenpy/RACE	中文 · Core EN · Extended
Synergistic	CORE	CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning	yeshenpy/CORE	中文 · Core EN · Extended
Reward design	Eureka	Human-Level Reward Design via Coding Large Language Models	eureka-research/Eureka	中文 1 · Core 中文 2 · Core EN 1 · Core EN 2 · Extended
Reward design	DrEureka	Language Model Guided Sim-to-Real Transfer	eureka-research/dreureka	EN · Extended
Reward design	LaRes	LaRes: Evolutionary Reinforcement Learning with LLM-Based Adaptive Reward Search	yeshenpy/LaRes	中文 · Core EN · Extended
Morphology	EvoGym	Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots	EvolutionGym/evogym	中文 1 · Core 中文 2 · Core EN 1 · Core EN 2 · Extended
Morphology	HERD	Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design	drdh/HERD	EN · Extended
Morphology	AIEA	Rapidly Evolving Soft Robots via Action Inheritance	HandingWangXDGroup/AIEA	Not found
Morphology	DERL	Embodied Intelligence via Learning and Evolution	agrimgupta92/derl	中文 · Core EN 1 · Core EN 2 · Extended
Morphology	TAME	Task-Agnostic Morphology Evolution	jhejna/morphology-opt	Not found

EA-assisted Optimization of RL

EA → RL · Evolutionary search supports reinforcement learning while RL remains responsible for solving the task.

↑ Overview · Next: RL-assisted EA →

EA-assisted Parameter Search

EA-assisted Action Selection

Browse all 11 methods

Method	Paper	Venue	Code	Guide
Qt-Opt	Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation	CoRL 2018	community reimplementation	中文 · Core EN · Core
CGP	Q-Learning for Continuous Actions with Cross-Entropy Guided Policies	ICML RL4RealLife 2019	Not found	Not found
EAS-RL	Evolutionary Action Selection for Gradient-Based Policy Learning	ICONIP 2022	Not found	Not found
SAC-CEPO	Soft Actor-Critic with Cross-Entropy Policy Optimization	Preprint 2021	wcgcyx/SAC-CEPO	Not found
GRAC	Self-Guided and Self-Regularized Actor-Critic	CoRL 2021	stanford-iprl-lab/GRAC	EN · Extended
OMAR	Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification	ICML 2022	ling-pan/OMAR	Not found
COMIX	Deep Multi-Agent RL for Decentralized Continuous Cooperative Control	Preprint 2020	oxwhirl/comix	Not found
NichGP-DRL	Niching Genetic Programming to Learn Actions for Deep Reinforcement Learning in Dynamic Flexible Scheduling	IEEE TEVC 2026 · early access 2024	MengXu95/NichGPDRL	Not found
ERL-A2S	Evolutionary Reinforcement Learning with Action Sequence Search for Imperfect Information Games	Information Sciences 2024	Not found	Not found
QD-ASE	Quality-Diversity Driven Action Swarm Evolution in Reinforcement Learning	IJCNN 2025	Not found	Not found
ERL-MPP	ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps	AAAI 2025	Not found	Not found

Hyperparameter Optimization

Algorithm and Update-rule Discovery

Other EA-assisted RL methods

Browse all 18 methods

Method	Paper	Venue	Code	Guide
GP-MAXQ	Evolutionary Development of Hierarchical Learning Structures	IEEE TEVC 2007	Not found	EN · Extended
PNS-RL	PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments	IROS 2021	Not found	Not found
Go-Explore	Go-Explore: a New Approach for Hard-Exploration Problems	arXiv 2019, rev. 2021	uber-research/go-explore	中文 1 · Core 中文 2 · Core EN 1 · Core EN 2 · Extended
G2N	Genetic-Gated Networks for Deep Reinforcement Learning	NeurIPS 2018	Not found	Not found
EVO-RL	Evolutionary-Driven Reinforcement Learning	GECCO 2021	Not found	Not found
ROMANCE	Robust Multi-Agent Coordination via Evolutionary Generation of Auxiliary Adversarial Attackers	AAAI 2023	zzq-bot/ROMANCE	Not found
MA3C	Communication-robust multi-agent learning by adaptable auxiliary multi-agent adversary generation	Frontiers of Computer Science 2024	Not found	中文 · Extended
EPC	Evolutionary Population Curriculum for Scaling Multi-Agent RL	ICLR 2020	qian18long/epciclr2020	EN · Extended
MAPPER	MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments	IROS 2020	Not found	中文 · Extended
EvIL	Evolution Strategies for Generalisable Imitation Learning	ICML 2024	SilviaSapora/evil	EN · Extended
Behaviour Distillation (HaDES)	Behaviour Distillation	ICLR 2024	FLAIROx/behaviour-distillation	Not found
Adversarial Cheap Talk (ACT)	Adversarial Cheap Talk	ICML 2023	luchris429/adversarial-cheap-talk	Not found
GP Offline Data	Using genetic programming to improve data collection for offline reinforcement learning	Swarm and Evolutionary Computation 2025	Not found	Not found
EDT Curriculum Goals	Hindsight Experience Replay with Evolutionary Decision Trees for Curriculum Goal Generation	EvoApplications 2024	Not found	Not found
GA Offline Dataset Reduction	Dataset Reduction for Offline Reinforcement Learning using Genetic Algorithms with Image-Based Heuristics	GECCO 2025	Not found	Not found
AEIRL	Adaptive Evolutionary Inverse Reinforcement Learning for Large-Scale Interconnected Systems	Neurocomputing 2026	Not found	Not found
ES-KD-MARL	Evolutionary Sampling for Knowledge Distillation in Multi-Agent Reinforcement Learning	Mathematics 2025	Not found	Not found
E2CL	Efficient Evolutionary Curriculum Learning for Scalable Multi-Agent Reinforcement Learning	Journal of King Saud University: Computer and Information Sciences 2025	Not found	Not found

RL-assisted Optimization of EA

RL → EA · Reinforcement learning configures or improves one or more stages of an evolutionary algorithm.

← EA-assisted RL · ↑ Overview · Next: Synergistic ERL →

Population Initialization

Population Evaluation

This branch contains seven primary RL-assisted evaluation works plus three secondary mechanism cross-lists. SC, PGPS, and ERL-Re2 remain counted only under their synergistic canonical branches.

Variation Operator

Browse all 8 canonical works

Method	Paper	Venue	Code	Guide
GPO	Policy Optimization by Genetic Distillation	—	Not found	EN · Extended
CEM-RL	Combining Evolutionary and Gradient-Based Methods for Policy Search	ICLR 2019	apourchot/CEM-RL	中文 · Extended EN · Extended
CEM-ACER	Guiding Evolutionary Strategies with Off-Policy Actor-Critic	—	Not found	Not found
PBRL	Population Based Reinforcement Learning	—	Not found	Not found
DEPRL	Diversity Evolutionary Policy Deep Reinforcement Learning	Complexity 2021	Not found	Not found
Wuji	Wuji: Automatic Online Combat Game Testing Using Evolutionary Deep Reinforcement Learning	ASE 2019	NeteaseFuxiRL/wuji	中文 · Core
PE-DRL	Stable and Sample-Efficient Policy Search for Continuous Control via Hybridizing Phenotypic Evolutionary Algorithm with the Double Actors Regularized Critics	GECCO 2023	Not found	Not found
EDA-PG	Evolutionary Deep Reinforcement Learning via Hybridizing Estimation-of-Distribution Algorithms with Policy Gradients	IEEE CEC 2024	Not found	Not found

Quality-Diversity

Browse all 15 canonical works

Method	Paper	Venue	Code	Guide
NS-RL	Efficient Novelty Search through Deep Reinforcement Learning	—	shilx001/NoveltySearch_Improvement	中文 · Extended
QD-PG	Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization	GECCO 2022	Not found	中文 · Extended
PGA-ME	Policy Gradient Assisted MAP-Elites	GECCO 2021	ollebompa/PGA-MAP-Elites	EN · Extended
GAC QD-RL	Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning	Preprint 2023	Not found	Not found
CMA-MEGA	Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning	GECCO 2022	icaros-usc/dqd-rl	EN 1 · Extended EN 2 · Extended
CCQD	Sample-Efficient Quality-Diversity by Cooperative Coevolution	ICLR 2024	lamda-bbo/CCQD	Not found
RefQD	Quality-Diversity with Limited Resources	GECCO 2024	lamda-bbo/RefQD	EN · Extended
QDHUAC	Distributional Value Estimation Without Target Networks for Robust Quality-Diversity	GECCO 2026 Full Paper	Not found	Not found
EDOCS	Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning	ICLR 2022	official code page	Not found
DvD	Effective Diversity in Population Based Reinforcement Learning	NeurIPS 2020	jparkerholder/DvD_ES	Not found
QD-Sim	Quality-Similar Diversity via Population Based Reinforcement Learning	ICLR 2023	Not found	Not found
NS-ES	Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents	NeurIPS 2018	Not found	Not found
CCNCS-ERL	Evolutionary Reinforcement Learning via Cooperative Coevolutionary Negatively Correlated Search	Swarm and Evolutionary Computation 2022	Not found	Not found
DBBD-ERL	Evolutionary reinforcement learning with density-based behavioral diversity enhancement for berth allocation and crane assignment	Swarm and Evolutionary Computation 2026	Not found	Not found
QDRL-BRPG	Quality-Diversity Reinforcement Learning using Behavior Regulated Policy Gradient	ACM TELO 2026	Not found	Not found

Dynamic Operator Selection

This branch was empty in the previous README. Survey v5 identifies sixteen methods.

Browse all 30 methods

Method	Paper	Venue	Code	Guide
RL-GA(a)	Controlling Genetic Algorithms with Reinforcement Learning	GECCO 2002	Not found	Not found
RLEP	Adaptive Evolutionary Programming Based on Reinforcement Learning	Information Sciences 2008	Not found	Not found
EA+RL	Increasing Efficiency of Evolutionary Algorithms by Choosing between Auxiliary Fitness Functions with Reinforcement Learning	ICMLA 2012	Not found	Not found
EA+RL(O)	Selecting Evolutionary Operators Using Reinforcement Learning: Initial Explorations	GECCO 2014	Not found	Not found
RL-GA(b)	RL-GA: A Reinforcement Learning-Based Genetic Algorithm for Electromagnetic Detection Satellite Scheduling Problem	Swarm and Evolutionary Computation 2023	Not found	Not found
GSF	Automated Design of Metaheuristics Using Reinforcement Learning within a Novel General Search Framework	IEEE TEVC 2023	Not found	Not found
MARLwCMA	Evolutionary Framework with Reinforcement Learning-Based Mutation Adaptation	IEEE Access 2020	Not found	Not found
MPSORL	Multi-strategy self-learning particle swarm optimization algorithm based on reinforcement learning	Mathematical Biosciences and Engineering 2023	Not found	Not found
DEDQN	Differential Evolution with Mixed Mutation Strategy Based on Deep Reinforcement Learning	Applied Soft Computing 2021	Not found	Not found
DE-DDQN	Deep Reinforcement Learning Based Parameter Control in Differential Evolution	GECCO 2019	Not found	Not found
RL-CORCO	Constrained Evolutionary Optimization Based on Reinforcement Learning Using the Objective Function and Constraints	Knowledge-Based Systems 2022	Not found	Not found
RL-HDE	Reinforcement Learning-Based Hybrid Differential Evolution for Global Optimization of Interplanetary Trajectory Design	Swarm and Evolutionary Computation 2023	Not found	Not found
DE-RLFR	Differential evolution based on reinforcement learning with fitness ranking for solving multimodal multiobjective problems	Swarm and Evolutionary Computation 2019	Not found	Not found
LRMODE	A Fitness Landscape Ruggedness Multiobjective Differential Evolution Algorithm with a Reinforcement Learning Strategy	Applied Soft Computing 2020	Not found	Not found
MOEA/D-DQN	Deep Reinforcement Learning Based Adaptive Operator Selection for Evolutionary Multi-Objective Optimization	IEEE TETCI 2023	Not found	Not found
AMODE-DRL	Scheduling of Continuous Annealing with a Multi-Objective Differential Evolution Algorithm Based on Deep Reinforcement Learning	IEEE T-ASE 2024	Not found	Not found
DRL-AEOSF	A Deep Reinforcement Learning-Assisted Evolutionary Operator Selection Framework for Constrained Optimization Problems	Swarm and Evolutionary Computation 2026	Not found	Not found
DRL-EMS	Deep Reinforcement Learning Based Environmental and Mating Selection for Evolutionary Multi-objective Optimization	GECCO 2026	Not found	Not found
DRL-MM-MOEA	A Deep Reinforcement Learning-Guided Multimodal Multi-Objective Evolutionary Algorithm with a Serial-Parallel Mechanism	Expert Systems with Applications 2026	Not found	Not found
RL-HH-OES	A Reinforcement Learning Hyper-Heuristic for Opposition-Enhanced Shuffled Multi-Strategy Evolutionary Algorithms with Adaptive Population Sizing	Applied Intelligence 2026	official data and MATLAB code	Not found
AOS-RL	Adaptive Operator Selection with Reinforcement Learning	Information Sciences 2021	Not found	Not found
OVEA	A Reference Vector Based Multiobjective Evolutionary Algorithm with Q-Learning for Operator Adaptation	Swarm and Evolutionary Computation 2023	Not found	Not found
RLDMDE	Dynamic Multi-Strategy Integrated Differential Evolution Algorithm Based on Reinforcement Learning for Optimization Problems	Complex & Intelligent Systems 2024	Not found	Not found
RL-AOS Runtime	Runtime Analysis of Adaptive Selection Variation Operators in Evolutionary Algorithm with Reinforcement Learning	Applied Intelligence 2025	Not found	Not found
GEA-AOS	Adaptive Operator Selection in Heuristic Optimization Utilizing Generalized Experience with Reinforcement Learning	International Journal of Parallel, Emergent and Distributed Systems 2025	Not found	Not found
TL-AOS	Transfer Learning for Operator Selection: A Reinforcement Learning Approach	Algorithms 2022	Not found	Not found
CEDE-DRL	Deep Reinforcement Learning Assisted Co-Evolutionary Differential Evolution for Constrained Optimization	Swarm and Evolutionary Computation 2023	Not found	Not found
DRL-AOS-CMO	Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection	IEEE/CAA Journal of Automatica Sinica 2024	Not found	Not found
RL-CMTO	A Reinforcement Learning Assisted Evolutionary Algorithm for Constrained Multi-Task Optimization	Information Sciences 2024	Not found	Not found
DRL-AOP	Deep Reinforcement Learning-Assisted Automated Operator Portfolio for Constrained Multi-Objective Optimization	IEEE TETCI 2026	Not found	Not found

Dynamic Algorithm Configuration

This maintained branch extends the survey's hyperparameter-configuration grouping to cover learned, state-dependent algorithm configuration. Survey v5 contains AGA, LTO, RL-DAC, REM, Q-LSHADE & DQ-HSES, MADAC, qlDE, and RLDE; GS-DAC is the round-2 addition.

Browse all 29 canonical works

Method	Paper	Venue	Code	Guide
AGA	Reinforcement Learning for Online Control of Evolutionary Algorithms	—	Not found	Not found
LTO	Learning Step-Size Adaptation in CMA-ES	—	automl/LTO-CMA	EN · Extended
RL-DAC	Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework	—	automl/DAC	EN · Extended
REM	Variational Reinforcement Learning for Hyper-Parameter Tuning of Adaptive Evolutionary Algorithm	—	Not found	Not found
MADAC	Multiagent Dynamic Algorithm Configuration	—	lamda-bbo/madac	EN · Extended
Q-LSHADE & DQ-HSES	Controlling Sequential Hybrid EA by Q-Learning	—	official code	Not found
qlDE	Q-Learning-Based Parameter Control in Differential Evolution for Structural Optimization	—	Not found	Not found
RLDE	Reinforcement Learning-Based Differential Evolution for Parameters Extraction of Photovoltaic Models	—	Not found	Not found
GS-DAC	Graph-Supported Dynamic Algorithm Configuration for Multi-Objective Combinatorial Optimization	ICML 2025	RobbertReijnen/GS-MODAC	Not found
ERLA-HBS	An Adaptive Evolutionary-Reinforcement Learning Algorithm for Hyperspectral Band Selection	Expert Systems with Applications 2024	Not found	Not found
ConfigX	ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning	AAAI 2025	MetaEvo/ConfigX	Not found
DRL-EA-CMO	Automated Configuration of Evolutionary Algorithms via Deep Reinforcement Learning for Constrained Multiobjective Optimization	IEEE TCYB 2025	Not found	Not found
RL-MS-ECMO	Reinforcement Learning-Assisted Multi-Stage Evolutionary Constrained Multi-Objective Optimization	ACM TELO 2025	Not found	Not found
AC-RL-MMO	Integrating Actor-Critic Reinforcement Learning With Evolutionary Algorithm for Multimodal Multiobjective Optimization	IEEE TNNLS 2026	Not found	Not found
RL-MMOF	A Hybrid Evolutionary Framework Assisted by Reinforcement Learning for Mixed Multi-Objective Optimization Features	Applied Soft Computing 2026	Not found	Not found
RL-EA Helicopter	Reinforcement Learning-Enhanced Evolutionary Algorithm for Multi-Objective Optimal Control of a Laboratory Helicopter	Swarm and Evolutionary Computation 2026	Not found	Not found
SuperDE	Deep Reinforcement Learning-Assisted Component Auto-Configuration of Differential Evolution Algorithm for Constrained Optimization: A Foundation Model	IEEE TEVC 2026	Not found	Not found
MetaMTO	Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking	IEEE TEVC 2026	Not found	Not found
LDE	Learning Adaptive Differential Evolution Algorithm From Optimization Experiences by Policy Gradient	IEEE TEVC 2021	yierh/LDE	Not found
RL-HPSDE	Differential Evolution with Hybrid Parameters and Mutation Strategies Based on Reinforcement Learning	Swarm and Evolutionary Computation 2022	Not found	Not found
RLDE-AFL	Reinforcement Learning-Based Self-Adaptive Differential Evolution Through Automated Landscape Feature Learning	GECCO 2025	MetaEvo/RLDE-AFL	Not found
RLDE-PFR	A Reinforcement Learning-Assisted Differential Evolution with Population Feature Replay	Engineering Applications of Artificial Intelligence 2026	Strive-code/rl-pfr	Not found
RL-PC-MOEA/D	Reinforcement Learning Aided Parameter Control in Multi-Objective Evolutionary Algorithm Based on Decomposition	Progress in Artificial Intelligence 2018	Not found	Not found
RL-AMH	Reinforcement Learning Based Adaptive Metaheuristics	GECCO 2022 Companion	Not found	Not found
RL-OGPA	Reinforcement Learning for Enhanced Online Gradient-Based Parameter Adaptation in Metaheuristics	Swarm and Evolutionary Computation 2023	Not found	Not found
DRL-DAS	Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution	IEEE TSMC: Systems 2024	Not found	Not found
DRL-PC-MOEC	Parameter Control Framework for Multiobjective Evolutionary Computation Based on Deep Reinforcement Learning	International Journal of Intelligent Systems 2024	Not found	Not found
KB-HPA-DE	Knowledge-Based Hyper-Parameter Adaptation of Multi-Stage Differential Evolution by Deep Reinforcement Learning	Neurocomputing 2025	Not found	Not found
RLCDE-LBFGS	Reinforcement Learning-Controlled Differential Evolution with L-BFGS Refinements	PLOS ONE 2026	Not found	Not found

Dynamic Resource Allocation

Other RL-assisted EA methods

Browse all 11 canonical works

Method	Paper	Venue	Code	Guide
Grad-CEM	Model-Predictive Control via Cross-Entropy and Gradient-Based Optimization	—	homangab/gradcem	Not found
LOOP	Learning Off-Policy with Online Planning	—	hari-sikchi/LOOP	EN · Core
TD-MPC	Temporal Difference Learning for Model Predictive Control	—	nicklashansen/tdmpc	中文 · Core EN 1 · Extended EN 2 · Extended
RGP	Reinforced Genetic Programming	—	Not found	Not found
GNP-RL	A Graph-Based Evolutionary Algorithm: Genetic Network Programming (GNP) and Its Extension Using Reinforcement Learning	—	Not found	Not found
RL-EAO-MWS	Reinforcement Learning-Assisted Evolutionary Auxiliary Optimization for Multi-Workflow Scheduling in Clouds	Swarm and Evolutionary Computation 2026	Not found	Not found
SSR-RL-EA	Self-Supervised State Representation for Reinforcement Learning-Assisted Evolutionary Algorithms	IEEE CEC 2026	Not found	Not found
SparseOp-DRL	Combining Sparse Evolutionary Operators and Deep Reinforcement Learning for Large-Scale Sparse Multiobjective Optimization Problems	Applied Soft Computing 2026	Not found	Not found
AutoMH	AutoMH: Automatically Create Evolutionary Metaheuristic Algorithms Using Reinforcement Learning	Entropy 2022	Not found	Not found
RL Acceptance Criteria	Reinforcement Learning Based Acceptance Criteria for Metaheuristic Algorithms	International Journal of Computational Intelligence Systems 2025	Not found	Not found
RL-RV-EMO	Reinforcement Learning and Reference Vector-Driven Expensive Multi-Objective Optimization	IEEE TEVC 2026	Not found	Not found

Synergistic Optimization of EA and RL

EA and RL both contribute directly to solving the task, either in a shared solution space or through decomposed subproblems.

Single-Agent Optimization

Browse all 35 canonical works

Method	Paper	Venue	Code	Guide
ERL	Evolution-Guided Policy Gradient in Reinforcement Learning	NeurIPS 2018	ShawK91/Evolutionary-Reinforcement-Learning	EN 1 · Extended EN 2 · Extended
CERL	Collaborative Evolutionary Reinforcement Learning	ICML 2019	intel/cerl	EN · Core
PDERL	Proximal Distilled Evolutionary Reinforcement Learning	AAAI 2020	crisbodnar/pderl	中文 · Extended
SC	A Surrogate-Assisted Controller for Expensive Evolutionary Reinforcement Learning	Information Sciences 2022	Yuxing-Wang-THU/Surrogate-assisted-ERL	中文 · Extended EN · Extended
GEATL	Evolutionary Reinforcement Learning for Sparse Rewards	GECCO 2021	Not found	Not found
CSPS	Cooperative Heterogeneous Deep Reinforcement Learning	NeurIPS 2020	Not found	Not found
T-ERL	Rethinking Population-Assisted Off-Policy Reinforcement Learning	GECCO 2023	Not found	Not found
ESAC	Off-Policy Evolutionary Reinforcement Learning with Maximum Mutations	AAMAS 2022	karush17/esac	Not found
PGPS	Coupling Policy Gradient with Population-Based Search	ICLR 2021 submission	Not found	Not found
VEB-RL	Value-Evolutionary-Based Reinforcement Learning	ICML 2024	yeshenpy/VEB-RL	中文 · Core EN · Extended
EvoRainbow / EvoRainbow-Exp	EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy Search	ICML 2024	yeshenpy/EvoRainbow	中文 · Core EN · Extended
ERL-TD	ERL-TD: Evolutionary Reinforcement Learning Enhanced with Truncated Variance and Distillation Mutation	AAAI 2024	2019cyf/ERL-TD	Not found
CORE	CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning	NeurIPS 2025	yeshenpy/CORE	中文 · Core EN · Extended
RIM	Recruitment-imitation mechanism for evolutionary reinforcement learning	Information Sciences 2021	Not found	Not found
PES	Proximal evolutionary strategy: improving deep reinforcement learning through evolutionary policy optimization	Memetic Computing 2024	Not found	Not found
RPSA-RL	Evolutionary Reinforcement Learning by Rank-one Evolution Strategy with Population Size Control	CIS 2023	Not found	Not found
EIERL	An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals	ACL 2025	Not found	Not found
Evo-RL for DPDP	A collaborative evolutionary reinforcement learning approach to dynamic pickup and delivery challenges	Transportation Research Part E: Logistics and Transportation Review 2026	Not found	Not found
NES-ERL	Neuroevolution Strategies for Episodic Reinforcement Learning	Journal of Algorithms 2009	Not found	Not found
Preference Racing	Preference-Based Reinforcement Learning: Evolutionary Direct Policy Search Using a Preference-Based Racing Algorithm	Machine Learning 2014	Not found	Not found
TRES	Trust Region Evolution Strategies	AAAI 2019	Not found	Not found
AMF-ERL	Adaptive Multifactorial Evolutionary Optimization for Multitask Reinforcement Learning	IEEE TEVC 2022	Not found	Not found
SOS	Exploring Safer Behaviors for Deep Reinforcement Learning	AAAI 2022	Not found	Not found
MO-PDERL	A Two-Stage Multi-Objective Evolutionary Reinforcement Learning Framework for Continuous Robot Control	GECCO 2023	Tran-Long/mopderl	Not found
Safety-Informed ERL	Evolutionary Reinforcement Learning: Hybrid Approach for Safety-Informed Fault-Tolerant Flight Control	Journal of Guidance, Control, and Dynamics 2024	Not found	Not found
ERLBioSeq	Designing Biological Sequences without Prior Knowledge Using Evolutionary Reinforcement Learning	AAAI 2024	Not found	Not found
EvOD	Scale Optimization Using Evolutionary Reinforcement Learning for Object Detection on Drone Imagery	AAAI 2024	UNNC-CV/EvOD	Not found
MO-ERL	Extending Evolution-Guided Policy Gradient Learning into the Multi-Objective Domain	Neurocomputing 2025	Not found	Not found
MCE-ERL	MCE-ERL: Evolutionary Reinforcement Learning Algorithm with Multi-Distribution Critics Evaluation	ICNSC 2025	Not found	Not found
Hetero-ERL	Heterogeneous Evolutionary Reinforcement Learning with Mixed Attention and Diffusion Model for Dynamic Seru Formation	Swarm and Evolutionary Computation 2026	Not found	Not found
EARL-NCO	Evolutionary Augmented Reinforcement Learning for Neural Combinatorial Optimization	IEEE TEVC 2026	Not found	Not found
PD-EPO	Preference-Driven Evolutionary Policy Optimization in Multi-Objective Reinforcement Learning	IEEE Access 2026	Not found	Not found
LLM-EA-HFSP	A Large Language Model-Assisted Reinforcement Learning Framework with Evolutionary Algorithm for Hybrid Flow-Shop Scheduling	IEEE TEVC 2026	Not found	Not found
ERL-WPSS	An Evolutionary Reinforcement Learning Framework for Joint Work Package Sizing and Scheduling with Uncertainties	European Journal of Operational Research 2026	Not found	Not found
ERL-ER-FedHG	ERL-ER-FedHG: Evolutionary Reinforcement Learning with Experience Replay for Federated Heterogeneous Graphs	Applied Soft Computing 2026	Not found	Not found

EvoRainbow and its experimental label refer to one paper and count once. CORE remains primarily single-agent ERL; solution-space/policy-space co-optimization is retained as a secondary tag, and its recent-work row is a non-counting cross-list.

Adaptive, Staged, or Stabilized Coupling

Representation and Search Decomposition

Multi-Agent Optimization

Reward Design

Reward search is split by mechanism so classical evolutionary reward search is not conflated with LLM-generated reward programs. Evo-Reward is counted here; EA-assisted reward search is a secondary tag only.

Browse all 12 canonical works

Non-LLM Evolutionary Reward Search

Method	Paper	Venue	Code	Guide
Evo-Reward	Genetic Programming for Reward Function Search	IEEE TAMD 2010	Not found	Not found
Co-Evolved Shaping Rewards	Co-Evolution of Shaping Rewards and Meta-Parameters in Reinforcement Learning	Adaptive Behavior 2008	Not found	Not found
Evolutionary Intrinsic Motivation	Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective	IEEE TAMD 2010	Not found	Not found
GP End-Goal Reward	Breaking Free from Hand-Crafted Rewards: A Genetic Programming Framework for End-Goal-Driven Reinforcement Learning	IEEE CEC 2026	Not found	Not found

LLM-based Reward Program Evolution

Method	Paper	Venue	Code	Guide
Eureka	Human-Level Reward Design via Coding Large Language Models	ICLR 2024	eureka-research/Eureka	中文 1 · Core 中文 2 · Core EN 1 · Core EN 2 · Extended
DrEureka	Language Model Guided Sim-to-Real Transfer	RSS 2024	eureka-research/dreureka	EN · Extended
ROSKA	Efficient Language-Instructed Skill Acquisition via Reward-Policy Co-Evolution	AAAI 2025	Not found	中文 · Core
R*	R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language Models	ICML 2025	Not found	中文 · Core
LaRes	LaRes: Evolutionary Reinforcement Learning with LLM-Based Adaptive Reward Search	NeurIPS 2025	yeshenpy/LaRes	中文 · Core EN · Extended
LERO	LERO: LLM-Driven Evolutionary Framework with Hybrid Rewards and Enhanced Observation for Multi-Agent Reinforcement Learning	ICIC 2025	Not found	Not found
ReMAC	ReMAC: Large Language Model-Driven Reward Design for Multi-Agent Manipulation Collaboration	NeurIPS Workshop 2025	Not found	EN · Extended
Physics-LLM Reward Evolution	Integrating Analytical Physics with LLM-Guided Reward Evolution in Reinforcement Learning	IEEE TEVC 2026	Not found	Not found

Morphological Evolution

Interpretable AI

Learning Classifier Systems

Frameworks, benchmarks, and tooling

These are non-canonical implementation, benchmark, or tooling resources and do not enter the 270-work or code-first counts. EvoGym is cross-listed with Morphological Evolution and counted once there.

Recent and emerging directions

Accepted papers are separated from canonical preprints and the non-counting watchlist. CORE and LaRes are cross-listed here for recency and are counted only in their primary synergistic branches.

Published or accepted

Canonical preprints and active submissions

Watchlist (not counted as canonical works)

Related surveys

• Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms
• Evolutionary Reinforcement Learning: A Survey
• Reinforcement Learning-Assisted Evolutionary Algorithm: A Survey and Research Opportunities
• Combining Evolution and Deep Reinforcement Learning for Policy Search: A Survey

Contributing

Please open an issue or pull request with:

1. the paper title and BibTeX;
2. an official paper URL (publisher, proceedings, arXiv, or OpenReview);
3. an author-maintained code URL, if available;
4. one taxonomy branch from this README;
5. one or two sentences explaining the EA-RL interaction.

To keep the list reliable, unofficial mirrors, generic search pages, and paper pages mislabeled as code will not be added.

Citation

@article{li2025bridging,
  author  = {Pengyi Li and Jianye Hao and Hongyao Tang and Xian Fu and Yan Zheng and Ke Tang},
  title   = {Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms},
  journal = {IEEE Transactions on Evolutionary Computation},
  year    = {2025},
  volume  = {29},
  number  = {5},
  pages   = {1707--1728},
  doi     = {10.1109/TEVC.2024.3443913}
}