arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.15085cs.LGcs.AIstat.ML
收藏

我能在这里做什么?强化学习中的示能性理论

What can I do here? A Theory of Affordances in Reinforcement Learning

Mila - McGill University(米拉 - 麦吉尔大学);DeepMind;Brown University(布朗大学)

Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, David Abel, Doina Precup

摘要:

强化学习算法通常假设所有动作对代理始终可用。然而,人和动物都理解环境特征与可行行动之间的一般联系。Gibson(1977)创造了“示能性”一词来描述这样一个事实,即在具体化的代理人的背景下,某些状态使代理人能够做某些动作。在本文中,我们开发了一个理论的启示代理人学习和计划在马尔可夫决策过程。在这种情况下,示能性起着双重作用。一方面,它们通过减少在任何特定情况下可用的行动数量,允许更快的规划。另一方面,它们有助于从数据中更有效和精确地学习过渡模型,特别是当这些模型需要函数近似时。我们建立这些属性,通过理论结果以及说明性的例子。我们还提出了一种学习启示的方法,并用它来估计更简单,更好地概括过渡模型。

英文摘要:

Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term "affordances" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reducing the number of actions available in any given situation. On the other hand, they facilitate more efficient and precise learning of transition models from data, especially when such models require function approximation. We establish these properties through theoretical results as well as illustrative examples. We also propose an approach to learn affordances and use it to estimate transition models that are simpler and generalize better.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑