QMDP-Net: Deep Learning for Planning under Partial Observability

Peter Karkus, David Hsu, Wee Sun Lee

Neural Information Processing Systems 

This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found