论文标题
学习持续控制中转移的态度抽象
Learning State Abstractions for Transfer in Continuous Control
论文作者
论文摘要
具有良好表示的简单算法可以解决具有挑战性的增强学习问题吗？在这项工作中，我们以肯定的方式回答了这个问题，其中我们将“简单的学习算法”为表格q学习，“良好的表示”是一个学习的国家抽象，而“具有挑战性的问题”是连续的控制任务。我们的主要贡献是一种学习算法，该算法将连续的状态空间抽象为离散的算法。我们将这种学识渊博的表示形式转移到看不见的问题以实现有效的学习。我们提供的理论表明，学到的抽象维持有限的价值损失，我们报告了实验表明，抽象赋予表格Q学习能力，以在看不见的任务中有效地学习。
Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be continuous control tasks. Our main contribution is a learning algorithm that abstracts a continuous state-space into a discrete one. We transfer this learned representation to unseen problems to enable effective learning. We provide theory showing that learned abstractions maintain a bounded value loss, and we report experiments showing that the abstractions empower tabular Q-Learning to learn efficiently in unseen tasks.
