Purpose in the Machine: Do Traffic Simulators Produce Distributionally Equivalent Outcomes for Reinforcement Learning Applications?
Rex ChenKathleen M. CarleyFei FangNorman M. SadehPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- network traffic
- multi agent
- state space
- optimal policy
- reinforcement learning algorithms
- policy search
- real time
- road traffic
- markov decision processes
- multi agent systems
- traffic flow
- temporal difference
- dynamic programming
- transportation networks
- internet traffic
- learning algorithm