Evolutionary and Coevolutionary Multi-Agent Design Choices and Dynamics

• URL: http://arxiv.org/abs/2507.05534v1
• Date: Mon, 07 Jul 2025 23:14:51 GMT
• Title: Evolutionary and Coevolutionary Multi-Agent Design Choices and Dynamics
• Authors: Erik Hemberg, Eric Liu, Lucille Fuller, Stephen Moskal, Una-May O'Reilly,
• Abstract summary: We evaluate agent learning when one side is trained to compete against a side that does not evolve and when two sides coevolve with each other.<n>Our versions of grammatical evolution algorithms using grammars that allow a controller to be expressed in code-like logic can achieve the best team performance.<n>Across the algorithms and representations, we observe that coevolution reduces the performance highs and lows of both sides while it induces fluctuations on both sides.
• Score: 4.180148451363464
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate two representation alternatives for the controllers of teams of cyber agents. We combine these controller representations with different evolutionary algorithms, one of which introduces a novel LLM-supported mutation operator. Using a cyber security scenario, we evaluate agent learning when one side is trained to compete against a side that does not evolve and when two sides coevolve with each other. This allows us to quantify the relative merits and tradeoffs of representation and algorithm combinations in terms of team performance. Our versions of grammatical evolution algorithms using grammars that allow a controller to be expressed in code-like logic can achieve the best team performance. The scenario also allows us to compare the performance impact and dynamics of coevolution versus evolution under different combinations. Across the algorithms and representations, we observe that coevolution reduces the performance highs and lows of both sides while it induces fluctuations on both sides. In contrast, when only one-side is optimized, performance peaks are higher and is more sustained than when both sides are optimized with coevolution.

Related papers

• Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence [131.41894248194995]
  We propose context-oriented decomposition adaptation (CorDA), a novel method that initializes adapters in a task-aware manner.<n>Thanks to the task awareness, our method enables two optional adaptation modes, knowledge-preserved mode (KPM) and instruction-previewed mode (IPM)
  arXiv  Detail & Related papers  (2025-06-16T07:55:14Z)
• Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning Operators [4.034672017339319]
  We introduce two new mutation operators that use layer activations to guide weight pruning.<n>One of these activation-informed operators outperforms random pruning, resulting in more efficient autoencoders.<n>We find that random pruning is better than guided pruning, in the coevolutionary setting.
  arXiv  Detail & Related papers  (2025-05-08T11:21:29Z)
• Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness [26.49261268883266]
  We study whether and how the choice optimization algorithm can impact group fairness in deep neural networks.<n>We show that the choice of optimization indeed influences fairness outcomes, particularly under severe imbalance.<n>Our results highlight the role of adaptive updates as a crucial mechanism for promoting fair outcomes.
  arXiv  Detail & Related papers  (2025-04-21T06:20:50Z)
• Strategies for optimizing double-bracket quantum algorithms [0.050257374758179374]
  We present strategies to optimize the choice of the double-bracket evolutions. We also present a selection of diagonal evolution parametrizations that can be directly compiled into CNOTs and single-qubit rotation gates.
  arXiv  Detail & Related papers  (2024-08-14T10:07:54Z)
• CompetEvo: Towards Morphological Evolution from Competition [60.69068909395984]
  We propose competitive evolution (CompetEvo), which co-evolves agents' designs and tactics in confrontation. The results reveal that our method enables agents to evolve a more suitable design and strategy for fighting.
  arXiv  Detail & Related papers  (2024-05-28T15:53:02Z)
• EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention [88.45459681677369]
  We propose a novel transformer variant with complex vector attention, named EulerFormer. It provides a unified theoretical framework to formulate both semantic difference and positional difference. It is more robust to semantic variations and possesses moresuperior theoretical properties in principle.
  arXiv  Detail & Related papers  (2024-03-26T14:18:43Z)
• Evolution Transformer: In-Context Evolutionary Optimization [6.873777465945062]
  We introduce Evolution Transformer, a causal Transformer architecture, which can flexibly characterize a family of Evolution Strategies. We train the model weights using Evolutionary Algorithm Distillation, a technique for supervised optimization of sequence models. We analyze the resulting properties of the Evolution Transformer and propose a technique to fully self-referentially train the Evolution Transformer.
  arXiv  Detail & Related papers  (2024-03-05T14:04:13Z)
• 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)
• Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers [109.52244418498974]
  We propose a novel textscAdmeta (textbfADouble exponential textbfMov averagtextbfE textbfAdaptive and non-adaptive momentum) framework. We provide two implementations, textscAdmetaR and textscAdmetaS, the former based on RAdam and the latter based on SGDM.
  arXiv  Detail & Related papers  (2023-07-02T18:16:06Z)
• Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning [18.20664209675016]
  This work focuses on equilibrium selection in no-conflict multi-agent games. Pareto Actor-Critic (Pareto-AC) is an actor-critic algorithm that maximises the returns of all agents.
  arXiv  Detail & Related papers  (2022-09-28T18:14:34Z)
• OneDConv: Generalized Convolution For Transform-Invariant Representation [76.15687106423859]
  We propose a novel generalized one dimension convolutional operator (OneDConv) It dynamically transforms the convolution kernels based on the input features in a computationally and parametrically efficient manner. It improves the robustness and generalization of convolution without sacrificing the performance on common images.
  arXiv  Detail & Related papers  (2022-01-15T07:44:44Z)
• X-volution: On the unification of convolution and self-attention [52.80459687846842]
  We propose a multi-branch elementary module composed of both convolution and self-attention operation. The proposed X-volution achieves highly competitive visual understanding improvements.
  arXiv  Detail & Related papers  (2021-06-04T04:32:02Z)

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.