Formulation and validation of a car-following model based on deep reinforcement learning.
Fabian HartOstap OkhrinMartin TreiberPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- model free
- function approximation
- reinforcement learning algorithms
- optimal control
- state space
- learning algorithm
- multi agent
- transfer learning
- set theoretic
- temporal difference learning
- fully unsupervised
- deep learning
- temporal difference
- markov decision processes
- optimal policy
- case study
- knowledge base