论文标题
基准测试质量多样性算法用于增强学习的神经进化
Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning
论文作者
论文摘要
我们提供了一个质量多样性基准套件，用于用于机器人控制的强化学习域中的深度神经进化。该套件包括任务，环境，行为描述符和健身的定义。我们根据任务的复杂性和由深神经网络控制的代理的复杂性指定不同的基准。基准测试使用标准质量多样性指标，包括覆盖范围，QD得分，最大健身和档案轮廓度量，以量化覆盖范围和健身之间的关系。我们还提出了如何通过引入相同指标的校正版本来量化解决方案对环境随机性的鲁棒性。我们认为，我们的基准是社区比较和改善其发现的宝贵工具。源代码可在线获得：https：//github.com/adaptive-intelligent-robotics/qdax
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control. The suite includes the definition of tasks, environments, behavioral descriptors, and fitness. We specify different benchmarks based on the complexity of both the task and the agent controlled by a deep neural network. The benchmark uses standard Quality-Diversity metrics, including coverage, QD-score, maximum fitness, and an archive profile metric to quantify the relation between coverage and fitness. We also present how to quantify the robustness of the solutions with respect to environmental stochasticity by introducing corrected versions of the same metrics. We believe that our benchmark is a valuable tool for the community to compare and improve their findings. The source code is available online: https://github.com/adaptive-intelligent-robotics/QDax
