What can you do with a rock? Affordance extraction via word embeddings
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Affordance DetectionReinforcement LearningReinforcement Learning (RL)Word EmbeddingsSimilar Papers 제목 키워드 기반
Affordance Extraction and Inference based on Semantic Role Labeling
Common-sense reasoning is becoming increasingly important for the advancement of Natural Language Processing. While word embeddings have been very successful, they cannot explain which aspects of 'coffee' and 'tea' make …
Common Sense ReasoningSemantic Role LabelingWord EmbeddingsWord SimilarityUnsupervised Inference of Object Affordance from Text Corpora
Affordances denote actions that can be performed in the presence of different objects, or possibility of action in an environment. In robotic systems, affordances and actions may suffer from poor semantic generalization …
ObjectWord EmbeddingsLOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding
Humans excel at acquiring knowledge through observation. For example, we can learn to use new tools by watching demonstrations. This skill is fundamental for intelligent systems to interact with the world. A key step to …
ObjectBinge Watching: Scaling Affordance Learning from Sitcoms
In recent years, there has been a renewed interest in jointly modeling perception and action. At the core of this investigation is the idea of modeling affordances(Affordances are opportunities of interaction in the scen…
Affordance Extraction with an External Knowledge Database for Text-Based Simulated Environments
Text-based simulated environments have proven to be a valid testbed for machine learning approaches. The process of affordance extraction can be used to generate possible actions for interaction within such an environmen…
valid