Generational Replacement and Learning for High-Performing and Diverse Populations in Evolvable Robots

• URL: http://arxiv.org/abs/2601.03807v1
• Date: Wed, 07 Jan 2026 11:11:57 GMT
• Title: Generational Replacement and Learning for High-Performing and Diverse Populations in Evolvable Robots
• Abstract summary: We show that combining generational replacement with intra-life learning can increase diversity while retaining performance.<n>We also highlight the importance of performance metrics when studying learning in morphologically evolving robots.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Evolutionary Robotics offers the possibility to design robots to solve a specific task automatically by optimizing their morphology and control together. However, this co-optimization of body and control is challenging, because controllers need some time to adapt to the evolving morphology - which may make it difficult for new and promising designs to enter the evolving population. A solution to this is to add intra-life learning, defined as an additional controller optimization loop, to each individual in the evolving population. A related problem is the lack of diversity often seen in evolving populations as evolution narrows the search down to a few promising designs too quickly. This problem can be mitigated by implementing full generational replacement, where offspring robots replace the whole population. This solution for increasing diversity usually comes at the cost of lower performance compared to using elitism. In this work, we show that combining such generational replacement with intra-life learning can increase diversity while retaining performance. We also highlight the importance of performance metrics when studying learning in morphologically evolving robots, showing that evaluating according to function evaluations versus according to generations of evolution can give different conclusions.

Related papers

• Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning [24.31239427177829]
  We show that morphological contributions to control learning decouple into two dimensions.<n>We propose AdaControl, which monitors disproportionate selection for morphological intelligence during evolution.<n>With AdaControl, a simple genetic algorithm rivals state-of-the-art generative-model-based co-design methods in discovering diverse high-performing designs.
  arXiv  Detail & Related papers  (2026-08-24T11:06:24Z)
• Co-Evolution in Agentic Systems: Toward Self-Directed Evolution Beyond Human Design [55.30329388138526]
  This survey focuses on co-evolution in agentic systems, a multi-component form of self-evolution in which multiple agents and their environment impose adaptive pressure on one another.<n>To organize existing papers, we propose a progressive three-stage taxonomy that traces how the system gradually sheds human-engineered constraints.
  arXiv  Detail & Related papers  (2026-08-10T23:10:40Z)
• Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery [55.951691393378354]
  We propose RoboCraft, a scalable humanoid co-design framework for fall recovery.<n>A shared policy pretrained across multiple designs is progressively finetuned on high-performing morphologies.<n>Experiments show that RoboCraft achieves an average performance gain of 44.55% on seven public humanoid robots.
  arXiv  Detail & Related papers  (2025-10-25T15:40:18Z)
• Evolution and learning in differentiable robots [0.0]
  We use differentiable simulations to rapidly and simultaneously optimize individual neural control of behavior across a large population of candidate body plans. Non-differentiable changes to the mechanical structure of each robot in the population were applied by a genetic algorithm in an outer loop of search. One of the highly differentiable morphologies discovered in simulation was realized as a physical robot and shown to retain its optimized behavior.
  arXiv  Detail & Related papers  (2024-05-23T15:45:43Z)
• DARLEI: Deep Accelerated Reinforcement Learning with Evolutionary Intelligence [77.78795329701367]
  We present DARLEI, a framework that combines evolutionary algorithms with parallelized reinforcement learning. We characterize DARLEI's performance under various conditions, revealing factors impacting diversity of evolved morphologies. We hope to extend DARLEI in future work to include interactions between diverse morphologies in richer environments.
  arXiv  Detail & Related papers  (2023-12-08T16:51:10Z)
• Universal Morphology Control via Contextual Modulation [52.742056836818136]
  Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies. We propose a hierarchical architecture to better model this dependency via contextual modulation.
  arXiv  Detail & Related papers  (2023-02-22T00:04:12Z)
• Co-evolving morphology and control of soft robots using a single genome [0.0]
  We present a new method to co-evolve morphology and control of robots. Our method derives both the "brain" and the "body" of an agent from a single genome and develops them together. We evaluate the presented methods on four tasks and observe that even if the search space was larger, having a single genome makes the evolution process converge faster.
  arXiv  Detail & Related papers  (2022-12-22T07:34:31Z)
• The Introspective Agent: Interdependence of Strategy, Physiology, and Sensing for Embodied Agents [51.94554095091305]
  We argue for an introspective agent, which considers its own abilities in the context of its environment. Just as in nature, we hope to reframe strategy as one tool, among many, to succeed in an environment.
  arXiv  Detail & Related papers  (2022-01-02T20:14:01Z)
• Co-optimising Robot Morphology and Controller in a Simulated Open-Ended Environment [1.4502611532302039]
  We show how changing the environment, where the agent locomotes, affects the convergence of morphologies. We show that agent-populations evolving in open-endedly evolving environments exhibit larger morphological diversity than agent-populations evolving in hand crafted curricula of environments.
  arXiv  Detail & Related papers  (2021-04-07T11:28:23Z)
• Population-Based Evolution Optimizes a Meta-Learning Objective [0.6091702876917279]
  We propose that meta-learning and adaptive evolvability optimize for high performance after a set of learning iterations. We demonstrate this claim with a simple evolutionary algorithm, Population-Based Meta Learning.
  arXiv  Detail & Related papers  (2021-03-11T03:45:43Z)
• Rapidly Adaptable Legged Robots via Evolutionary Meta-Learning [65.88200578485316]
  We present a new meta-learning method that allows robots to quickly adapt to changes in dynamics. Our method significantly improves adaptation to changes in dynamics in high noise settings. We validate our approach on a quadruped robot that learns to walk while subject to changes in dynamics.
  arXiv  Detail & Related papers  (2020-03-02T22:56:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.