A Reinforcement Learning Approach to the Orienteering Problem with Time Windows.
Ricardo GamaHugo L. FernandesPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- vehicle routing problem
- function approximation
- temporal difference
- dynamic programming
- markov decision processes
- optimal policy
- state space
- model free
- learning algorithm
- learning process
- routing problem
- reinforcement learning algorithms
- transfer learning
- control problems
- vehicle routing
- optimal control
- traveling salesman problem
- multi agent
- optimization problems
- supervised learning
- least squares
- case study
- website
- machine learning
- action space
- data sets