Poster
The Natural Language of Actions
Guy Tennenholtz · Shie Mannor
Pacific Ballroom #41
Keywords: [ Clustering ] [ Deep Reinforcement Learning ] [ Natural Language Processing ] [ Representation Learning ] [ Transfer and Multitask Learning ]
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.
Live content is unavailable. Log in and register to view live content