Quality-Diversity (QD) algorithms are powerful exploration algorithms that
allow robots to discover large repertoires of diverse and high-performing
skills. However, QD algorithms are sample inefficient and require millions of
evaluations. In this paper, we propose Dynamics-Aware Quality-Diversity
(DA-QD), a framework to improve the sample efficiency of QD algorithms through
the use of dynamics models. We also show how DA-QD can then be used for
continual acquisition of new skill repertoires. To do so, we incrementally
train a deep dynamics model from experience obtained when performing skill
discovery using QD. We can then perform QD exploration in imagination with an
imagined skill repertoire. We evaluate our approach on three robotic
experiments. First, our experiments show DA-QD is 20 times more sample
efficient than existing QD approaches for skill discovery. Second, we
demonstrate learning an entirely new skill repertoire in imagination to perform
zero-shot learning. Finally, we show how DA-QD is useful and effective for
solving a long horizon navigation task and for damage adaptation in the real
world. Videos and source code are available at:
this https URL

通过使用动态模型来提高质量 - 多样性算法的样本效率，我们提出了动态感知质量 - 多样性 (DA-QD) 框架；我们从中获得的经验进行增量训练，可以在想象力中使用想象技能库进行质量 - 多样性探索。该方法能够在三个机器人实验中取得成功的应用，包括比现有 QD 方法更高效的技能发现、零 - shot 学习中的新技能库以及长期导航任务中的损伤适应。