Deep Reinforcement Learning to Maximize Arterial Usage during Extreme Congestion.
Ashutosh DuttaMilan JainArif KhanArun V. SathanurPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- congestion control
- model free
- temporal difference
- multi agent
- optimal control
- blood pressure
- deep learning
- transfer learning
- optimal policy
- dynamic programming
- blood flow
- learning algorithm
- data sets
- dynamic routing
- usage patterns
- ip networks
- supervised learning
- learning process
- machine learning