论文标题
级联属性网络：使用分层神经网络分解加强学习控制政策
Cascade Attribute Network: Decomposing Reinforcement Learning Control Policies using Hierarchical Neural Networks
论文作者
论文摘要
已经开发了强化学习方法，以在各种自动化任务中的培训控制政策方面取得巨大成功。但是，在实际自动化中加强学习的更广泛应用的主要挑战是，在其他类似情况下，训练过程很难重复使用，并且预验证的策略网络几乎不可重复使用。为了解决此问题，我们提出了Cascade属性网络（CAN），该网络利用其层次结构来分解复杂的控制策略，以要求在控制任务中编码的要求限制（我们称之为属性）。我们验证了我们提出的方法在具有各种附加属性的两个机器人控制方案上的有效性。对于某些具有多个附加属性属性的控制任务，通过直接组装Cascade中的属性模块，可以以零拍的方式提供理想的控制策略。
Reinforcement learning methods have been developed to achieve great success in training control policies in various automation tasks. However, a main challenge of the wider application of reinforcement learning in practical automation is that the training process is hard and the pretrained policy networks are hardly reusable in other similar cases. To address this problem, we propose the cascade attribute network (CAN), which utilizes its hierarchical structure to decompose a complicated control policy in terms of the requirement constraints, which we call attributes, encoded in the control tasks. We validated the effectiveness of our proposed method on two robot control scenarios with various add-on attributes. For some control tasks with more than one add-on attribute attribute, by directly assembling the attribute modules in cascade, the CAN can provide ideal control policies in a zero-shot manner.
