大型多智能体环境中非情景神经进化的生态演化动力学
Eco-evolutionary Dynamics of Non-episodic Neuroevolution in Large Multi-agent Environments
AI总结：
提出一种无环境和种群重置的非情景多智能体神经进化方法，在JAX加速的大型网格世界中利用可演化循环神经网络控制智能体局部繁殖，证明了该方法能找到可持续的集体觅食策略。
摘要：
神经进化（NE）近期已被证明是强化学习任务中基于梯度下降学习的一种有竞争力的替代方案。然而，大多数NE方法及相关仿真环境与生物进化存在关键差异：环境在每一代结束时被重置为初始条件，而自然环境不断被其居民所改变；智能体基于在种群内最大化奖励的能力进行繁殖，而生物有机体基于取决于其资源消耗的内部生理变量进行繁殖和死亡；仿真环境主要是单智能体的，而生物世界本质上多智能体并与种群共同演化。在本研究中，我们提出了一种在没有任何环境或种群重置的情况下持续演化自适应智能体的方法。该环境是一个具有复杂时空资源生成的大型网格世界，包含许多智能体，每个智能体由一个可演化的循环神经网络控制，并基于其内部生理学进行局部繁殖。整个系统在JAX中实现，允许在GPU上进行极快速的仿真。我们表明，NE可以在生态有效的非情景多智能体环境中运行，在生态与演化动力学之间复杂的相互作用下，找到可持续的集体觅食策略。
英文摘要：
Neuroevolution (NE) has recently proven a competitive alternative to learning by gradient descent in reinforcement learning tasks. However, the majority of NE methods and associated simulation environments differ crucially from biological evolution: the environment is reset to initial conditions at the end of each generation, whereas natural environments are continuously modified by their inhabitants; agents reproduce based on their ability to maximize rewards within a population, while biological organisms reproduce and die based on internal physiological variables that depend on their resource consumption; simulation environments are primarily single-agent while the biological world is inherently multi-agent and evolves alongside the population. In this work we present a method for continuously evolving adaptive agents without any environment or population reset. The environment is a large grid world with complex spatiotemporal resource generation, containing many agents that are each controlled by an evolvable recurrent neural network and locally reproduce based on their internal physiology. The entire system is implemented in JAX, allowing very fast simulation on a GPU. We show that NE can operate in an ecologically-valid non-episodic multi-agent setting, finding sustainable collective foraging strategies in the presence of a complex interplay between ecological and evolutionary dynamics.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
