Abstract Just like humans, robots can improve their performance by practicing, i. e. by performing the desired behavior many times and updating the underlying skill representation using the newly gathered data. In this paper, we propose to implement robot practicing by applying statistical and reinforcement learning (RL) in a latent space of the selected skill representation. The latent space is computed by a deep autoencoder neural network, with the data to train the network generated in simulation. However, we show that the resulting latent space representation is useful also for learning on a real robot. Our simulation and real-world results demonstrate that by exploiting the latent space of the underlying motor skill representation, a significant reduction of the amount of data needed for effective learning by Gaussian Process Regression (GPR) can be achieved. Similarly, the number of RL epochs can be significantly reduced. Finally, it is evident from our results that an autoencoder-based latent space is more effective for these purposes than a latent space computed by principal component analysis.

中文翻译：

---

深度自编码神经网络潜在空间中的机器人技能学习

摘要 就像人类一样，机器人可以通过练习来提高自己的表现，即。e. 通过多次执行所需的行为并使用新收集的数据更新基础技能表示。在本文中，我们建议通过在所选技能表示的潜在空间中应用统计和强化学习 (RL) 来实现机器人练习。潜在空间由深度自动编码器神经网络计算，并在模拟中生成训练网络的数据。然而，我们表明，由此产生的潜在空间表示对于在真实机器人上学习也很有用。我们的模拟和现实世界的结果表明，通过利用潜在运动技能表示的潜在空间，可以通过高斯过程回归 (GPR) 显着减少有效学习所需的数据量。类似地，可以显着减少 RL epoch 的数量。最后，从我们的结果中可以明显看出，对于这些目的，基于自动编码器的潜在空间比通过主成分分析计算的潜在空间更有效。