Reinforcement Learning Applied to the Dynamic Capacitated Profitable Tour Problem with Stochastic Requests.

Marvin Caspar Oliver Wendt

Published in: ICCSA (1) (2024)

Keyphrases

reinforcement learning
routing problem
neural network
dynamic environments
direct policy search
markov chain
metaheuristic
multistage
monte carlo
optimal control
lot sizing
learning automata
single source