Lamarckian Inheritance Improves Robot Evolution in Dynamic Environments

no code implementations • 28 Mar 2024 • Jie Luo, Karine Miras, Carlo Longhi, Oliver Weissl, Agoston E. Eiben

This study explores the integration of Lamarckian system into evolutionary robotics (ER), comparing it with the traditional Darwinian model across various environments.

A comparison of controller architectures and learning mechanisms for arbitrary robot morphologies

no code implementations • 25 Sep 2023 • Jie Luo, Jakub Tomczak, Karine Miras, Agoston E. Eiben

The main question this paper addresses is: What combination of a robot controller and a learning method should be used, if the morphology of the learning robot is not known in advance?

Reinforcement Learning (RL)

Lamarck's Revenge: Inheritance of Learned Traits Can Make Robot Evolution Better

no code implementations • 22 Sep 2023 • Jie Luo, Karine Miras, Jakub Tomczak, Agoston E. Eiben

We research this issue through simulations with an evolutionary robot framework where morphologies (bodies) and controllers (brains) of robots are evolvable and robots also can improve their controllers through learning during their lifetime.

Open-endedness induced through a predator-prey scenario using modular robots

no code implementations • 20 Sep 2023 • Dimitri Kachler, Karine Miras

This work investigates how a predator-prey scenario can induce the emergence of Open-Ended Evolution (OEE).

EvoMan: Game-playing Competition

1 code implementation • 22 Dec 2019 • Fabricio Olivetti de Franca, Denis Fantinato, Karine Miras, A. E. Eiben, Patricia A. Vargas

For this particular competition, the main goal is to beat all of the eight bosses using a generalist strategy.