Login / Signup
CP-MDP: A CANDECOMP-PARAFAC Decomposition Approach to Solve a Markov Decision Process Multidimensional Problem.
Daniela Kuinchtner
Afonso Sales
Felipe Meneguzzi
Published in:
CoRR (2021)
Keyphrases
</>
optimal policy
markov decision process
tensor decomposition
markov decision processes
reward function
high order
inverse reinforcement learning
reinforcement learning
dynamic programming
state space
linear programming
linear program
multi dimensional
low rank
finite state
decomposition algorithm