LGDec 20, 2013
Learning States Representations in POMDP
arXiv:1312.6042v41 citations
Originality Synthesis-oriented
AI Analysis
This addresses the challenge of decision-making under uncertainty for AI and robotics applications, but appears incremental as it builds on existing representation learning methods.
The authors tackled the problem of learning policies in partially observable Markov decision processes (POMDPs) by developing a latent representation space, resulting in accurate policy learning.
We propose to deal with sequential processes where only partial observations are available by learning a latent representation space on which policies may be accurately learned.