Learning Action Representations for Reinforcement Learning

Yash Chandak
Yash Chandak
James Kostas
James Kostas

International Conference on Machine Learning, pp. 941-950, 2019.

Cited by: 25|Bibtex|Views4
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

Most model-free reinforcement learning methods leverage state representations (embeddings) for generalization, but either ignore structure in the space of actions or assume the structure is provided a priori. We show how a policy can be decomposed into a component that acts in a low-dimensional space of action representations and a comp...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments