paper-with-me

홈 › Papers

Why Evolve When You Can Adapt? Post-Evolution Adaptation of Genetic Memory for On-the-Fly Control

2025-08-05 · Hamze Hammami, Eva Denisa Barbulescu, Talal Shaikh, Mouayad Aldada, Muhammad Saad Munawar arxiv

Imagine a robot controller with the ability to adapt like human synapses, dynamically rewiring itself to overcome unforeseen challenges in real time. This paper proposes a novel zero-shot adaptation mechanism for evolutionary robotics, merging a standard Genetic Algorithm (GA) controller with online Hebbian plasticity. Inspired by biological systems, the method separates learning and memory, with the genotype acting as memory and Hebbian updates handling learning. In our approach, the fitness function is leveraged as a live scaling factor for Hebbian learning, enabling the robot's neural controller to adjust synaptic weights on-the-fly without additional training. This adds a dynamic adaptive layer that activates only during runtime to handle unexpected environmental changes. After the task, the robot 'forgets' the temporary adjustments and reverts to the original weights, preserving core knowledge. We validate this hybrid GA-Hebbian controller on an e-puck robot in a T-maze navigation task with changing light conditions and obstacles.

📄 PDF Abstract BibTeX arXiv:2508.03600

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems

2020-04-27 · Eseoghene Ben-Iwhiwhu, Pawel Ladosz, Jeffery Dick, Wen-Hua Chen 외

Rapid online adaptation to changing tasks is an important problem in machine learning and, recently, a focus of meta-reinforcement learning. However, reinforcement learning (RL) algorithms struggle in POMDP environments …

Meta Reinforcement LearningMinecraftreinforcement-learningReinforcement Learning+1

Position: Agentic Evolution is the Path to Evolving LLMs

2026-01-30 · Minhua Lin, Hanqing Lu, Zhan Shi, Bing He 외 arxiv

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Sc…

Synthetic Counteradaptation: A Principle of Human-AI Co-evolution

2026-03-31 · Ivar Frisch, Jackie Kay, Philip Moreira Tomei arxiv

In this paper, we introduce the concept of synthetic counteradaptation, a process where human and AI systems co-evolve by adapting to each other's strategies and behaviors. Synthetic counteradaptation occurs when AI syst…

Game of Go

Evolutionary adaptation is facilitated by the presence of lethal genotypes

2023-01-18 · Viktoria Blavatska, Bartlomiej Waclaw

The adaptation rate in theoretical models of biological evolution increases with the mutation rate but only to a point when mutations into lethal states cause extinction. One would expect that removing such states should…

A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

2025-07-28 · Huan-ang Gao, Jiayi Geng, Wenyue Hua, Mengkang Hu 외 arxiv

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks but remain fundamentally static, unable to adapt their internal parameters to novel tasks, evolving knowledge domains, or dynami…

Continual Learning