What can you do with a rock? Affordance extraction via word embeddings
Nancy Fulda Daniel Ricks Ben Murdoch David Wingate {nfulda, daniel_ricks, murdoch, Brigham Young University
Abstract
Autonomous agents must often detect affordances: the set of behaviors enabled by a situation. Affordance detection is particularly helpful in domains with large action spaces, allowing the agent to prune its search space by avoiding futile behaviors. This paper presents a method for affordance extraction via word embeddings trained on a Wikipedia corpus. The resulting word vectors are treated as a common knowledge database which can be queried using linear algebra. We apply this method to a reinforcement learning agent in a text-only environment and show that affordance-based action selection improves performance most of the time. Our method increases the computational complexity of each learning step but significantly reduces the total number of steps needed. In addition, the agent’s action selections begin to resemble those a human would choose.
中文速览
自动智能体在复杂环境中行动时，常常浪费大量时间去尝试毫无意义的操作，根本原因在于它缺乏人类那种"什么事情能做、什么事情做了没用"的常识判断能力（可供性/affordance检测）。研究者提出用维基百科语料训练的词向量（word embeddings，即word2vec）来充当常识知识库，通过简单的向量加减运算查询"对某个物体该用什么动词"以及"哪些物体是可以被操作的"，从而为智能体在行动前先筛掉不合理的选项。他们把这套方法接入一个基于文字的冒险游戏强化学习智能体，结果显示：引入可供性筛选后，智能体在绝大多数情况下能更快找到有效行为，所需学习步数大幅减少，而且它选出的动作开始接近人类玩家的自然选择。这项工作的意义在于，它证明了无需手工构建结构化知识库，仅凭大规模在线文本中隐式编码的语义关系就能有效压缩智能体的搜索空间，为让机器像人一样"只做有意义的事"提供了一条轻量可行的路径。
原文 arXiv:1703.03429;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1703.03429v1