The Natural Language of Actions
arXiv:1902.01119
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.
arXiv commentPublished in the proceedings of the 36th International Conference on Machine Learning (ICML 2019)
References in corpus (6)
- Efficient Estimation of Word Representations in Vector Space
- Distributed Representations of Words and Phrases and their Compositionality
- An Overview of Multi-Task Learning in Deep Neural Networks
- StarCraft II: A New Challenge for Reinforcement Learning
- Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
- Learning Relevant Features for Manipulation Skills using Meta-Level Priors