论文标题
增强性拓扑代理用于开放式学习
Augmentative Topology Agents For Open-Ended Learning
论文作者
论文摘要
在这项工作中，我们通过引入一种同时发展代理和越来越具有挑战性的环境的方法来解决开放式学习的问题。与以前使用固定神经网络拓扑优化代理的开放式方法不同，我们假设可以通过允许代理的控制器遇到更困难的环境来改善概括。我们的方法，增强拓扑EPOET（ATEP），扩展了增强的配对开放式开拓者（EPOET）算法，通过允许代理随着时间的推移发展自己的神经网络结构，并在必要时增加了复杂性和容量。经验结果表明，与固定型基线相比，能够求解更多环境的一般代理中的ANEP结果。我们还研究了在环境之间转移试剂的机制，并发现基于物种的方法进一步改善了剂的性能和概括。
In this work, we tackle the problem of open-ended learning by introducing a method that simultaneously evolves agents and increasingly challenging environments. Unlike previous open-ended approaches that optimize agents using a fixed neural network topology, we hypothesize that generalization can be improved by allowing agents' controllers to become more complex as they encounter more difficult environments. Our method, Augmentative Topology EPOET (ATEP), extends the Enhanced Paired Open-Ended Trailblazer (EPOET) algorithm by allowing agents to evolve their own neural network structures over time, adding complexity and capacity as necessary. Empirical results demonstrate that ATEP results in general agents capable of solving more environments than a fixed-topology baseline. We also investigate mechanisms for transferring agents between environments and find that a species-based approach further improves the performance and generalization of agents.
