Login / Signup
Maintenance Strategies for Sewer Pipes with Multi-State Degradation and Deep Reinforcement Learning.
Lisandro Arturo Jimenez-Roa
Thiago D. Simão
Zaharah Allah Bukhsh
Tiedo Tinga
Hajo Molegraaf
Nils Jansen
Mariëlle Stoelinga
Published in:
CoRR (2024)
Keyphrases
</>
reinforcement learning
state space
function approximation
learning algorithm
knowledge base
dynamic programming
supervised learning
optimal policy
markov decision processes
initial state
markov decision process
function approximators
state action
transition model