Deep reinforcement learning for stochastic last-mile delivery with crowdshipping.
Marco SilvaJoão Pedro PedrosoAna VianaPublished in: EURO J. Transp. Logist. (2023)
Keyphrases
- reinforcement learning
- direct policy search
- stochastic approximation
- learning automata
- function approximation
- monte carlo
- model free
- robotic control
- model free reinforcement learning
- control policies
- temporal difference
- state space
- optimal policy
- markov decision processes
- learning process
- multi agent
- machine learning
- supervised learning
- data sets
- learning algorithm
- continuous state spaces
- stochastic optimization
- stochastic model
- deep learning
- function approximators
- bayesian networks
- case study
- objective function
- stochastic nature
- markov decision process
- action selection