Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics
The paper discusses the role of Lamarckian inheritance in the evolution of robotic agents in dynamic environments. It highlights how the effectiveness of this inheritance depends on the predictability and conflict of environmental changes. The authors demonstrate that adding sensors can enhance the performance of Lamarckian inheritance under challenging conditions.
- ▪The study combines morphology optimization with controller optimization in robotic evolution.
- ▪Lamarckian inheritance can improve performance in dynamic environments, contrary to traditional evolutionary theory.
- ▪The benefits of Lamarckian inheritance are influenced by the predictability and conflict of environmental changes.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Robotics arXiv:2605.15769 (cs) [Submitted on 15 May 2026] Title:Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics Authors:K. Ege de Bruin, Kyrre Glette, Kai Olav Ellefsen View a PDF of the paper titled Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics, by K. Ege de Bruin and 2 other authors View PDF Abstract:The co-optimization of a robot's body and brain presents a coupled challenge: the morphology constrains which control strategies are effective, while the control determines how well the morphology performs.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
