Login / Signup

Learning Partially Observable Markov Decision Processes Using Coupled Canonical Polyadic Decomposition.

Kejun HuangZhuoran YangZhaoran WangMingyi Hong
Published in: DSW (2019)
Keyphrases
  • predictive state representations
  • partially observable markov decision processes
  • learning algorithm
  • reinforcement learning
  • decision problems
  • search space
  • special case
  • probabilistic model
  • optimal policy