papers AI Learner
The Github is limit! Click to go to the new site.

The Natural Language of Actions

2019-02-04
Guy Tennenholtz, Shie Mannor

Abstract

We introduce Act2Vec, a general framework for learning context-based action representation for Reinforcement Learning. Representing actions in a vector space help reinforcement learning algorithms achieve better performance by grouping similar actions and utilizing relations between different actions. We show how prior knowledge of an environment can be extracted from demonstrations and injected into action vector representations that encode natural compatible behavior. We then use these for augmenting state representations as well as improving function approximation of Q-values. We visualize and test action embeddings in three domains including a drawing task, a high dimensional navigation task, and the large action space domain of StarCraft II.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.01119

PDF

http://arxiv.org/pdf/1902.01119


Similar Posts

Comments