论文标题
对抗性技巧学习以进行强大的操纵
Adversarial Skill Learning for Robust Manipulation
论文作者
论文摘要
深厚的强化学习在机器人操纵任务上取得了重大进展，并且在理想的无干扰环境中效果很好。但是，在现实世界中，内部和外部干扰都是不可避免的，因此训练有素的政策的绩效将大大下降。为了提高政策的鲁棒性，我们将对抗性训练机制介绍给本文的机器人操纵任务，并提出了基于软演员 - 批评（SAC）的对抗技巧学习算法，以进行健壮的操纵。进行了广泛的实验，以证明学习政策对内部和外部干扰是可靠的。此外，在模拟环境和实际机器人平台上都评估了所提出的算法。
Deep reinforcement learning has made significant progress in robotic manipulation tasks and it works well in the ideal disturbance-free environment. However, in a real-world environment, both internal and external disturbances are inevitable, thus the performance of the trained policy will dramatically drop. To improve the robustness of the policy, we introduce the adversarial training mechanism to the robotic manipulation tasks in this paper, and an adversarial skill learning algorithm based on soft actor-critic (SAC) is proposed for robust manipulation. Extensive experiments are conducted to demonstrate that the learned policy is robust to internal and external disturbances. Additionally, the proposed algorithm is evaluated in both the simulation environment and on the real robotic platform.
