Deep Reinforcement Learning Approach to Solve Dynamic Vehicle Routing Problem with Stochastic Customers.
Waldy JoeHoong Chuin LauPublished in: ICAPS (2020)
Keyphrases
- reinforcement learning
- direct policy search
- stochastic approximation
- state space
- mathematical programming
- stochastic control
- stochastic methods
- control policies
- learning automata
- function approximation
- optimal policy
- markov chain
- website
- markov decision processes
- neural network
- model free
- control problems
- stochastic processes
- dynamical systems
- multi agent reinforcement learning
- multi agent
- learning algorithm