Evolutionary Algorithm for Reservoir Learning and Yielding

arXiv cs.AI Papers

Summary

Introduces EARLY, an evolutionary framework for evolving multi-reservoir Echo State Networks that outperforms random search on temporal learning tasks and exhibits task-dependent structural differences.

arXiv:2605.30372v1 Announce Type: cross Abstract: Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer. However, classical Echo State Networks (ESNs) often require task-specific tuning of their architecture and hyperparameters to achieve good performance. This paper introduces EARLY (Evolutionary Algorithm for Reservoir Learning and Yielding), a framework designed to evolve both the topology and hyperparameters of multi-reservoir ESNs. Inspired by the modular organisation of the brain, EARLY encodes architectures as graph-based genomes and applies crossover, mutation, and selection to discover effective configurations. Our goal is to create both generic architectures and tasks inducing generalization. The method is evaluated on temporal learning tasks from the CogScale dataset. Results show that evolved architectures outperform those obtained with random search on several tasks and exhibit structural differences depending on task difficulty: simpler tasks yield lightweight architectures, while more complex tasks favour richer modular organisations. These findings suggest that evolutionary search can help identify reusable reservoir structures for a broader range of temporal problems. The evolved architectures are further evaluated on a cross-situational learning dataset to assess their ability to adapt to new environments.
Original Article
View Cached Full Text

Cached at: 06/01/26, 09:29 AM

# Evolutionary Algorithm for Reservoir Learning and Yielding
Source: [https://arxiv.org/abs/2605.30372](https://arxiv.org/abs/2605.30372)
[View PDF](https://arxiv.org/pdf/2605.30372)

> Abstract:Reservoir computing, a type of recurrent neural network, is a promising approach for temporal learning as it separates dynamic processing from the trained readout layer\. However, classical Echo State Networks \(ESNs\) often require task\-specific tuning of their architecture and hyperparameters to achieve good performance\. This paper introduces EARLY \(Evolutionary Algorithm for Reservoir Learning and Yielding\), a framework designed to evolve both the topology and hyperparameters of multi\-reservoir ESNs\. Inspired by the modular organisation of the brain, EARLY encodes architectures as graph\-based genomes and applies crossover, mutation, and selection to discover effective configurations\. Our goal is to create both generic architectures and tasks inducing generalization\. The method is evaluated on temporal learning tasks from the CogScale dataset\. Results show that evolved architectures outperform those obtained with random search on several tasks and exhibit structural differences depending on task difficulty: simpler tasks yield lightweight architectures, while more complex tasks favour richer modular organisations\. These findings suggest that evolutionary search can help identify reusable reservoir structures for a broader range of temporal problems\. The evolved architectures are further evaluated on a cross\-situational learning dataset to assess their ability to adapt to new environments\.

## Submission history

From: Julien Testu \[[view email](https://arxiv.org/show-email/a4cf769c/2605.30372)\] \[via CCSD proxy\] **\[v1\]**Tue, 19 May 2026 11:22:21 UTC \(4,592 KB\)

Similar Articles

Evolution strategies as a scalable alternative to reinforcement learning

OpenAI Blog

OpenAI presents evolution strategies (ES) as a scalable black-box optimization alternative to reinforcement learning for training neural network policies. ES simplifies the optimization problem by treating policy training as a stochastic parameter search that repeatedly samples and selects better parameter configurations based on reward feedback.

Evolved Policy Gradients

OpenAI Blog

OpenAI introduces Evolved Policy Gradients (EPG), a meta-learning approach that learns loss functions through evolution rather than learning policies directly, enabling RL agents to generalize better across tasks by leveraging prior experience similar to how humans transfer skills.

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

Hugging Face Daily Papers

This paper introduces AEM, a supervision-free method for agentic reinforcement learning that adapts entropy dynamics at the response level to improve exploration-exploitation trade-offs. It demonstrates performance gains on benchmarks like ALFWorld and SWE-bench by aligning uncertainty estimation with action granularity.