Microscopic Model-Based RL Approaches for Traffic Signal Control Generalize Better than Model-Free RL Approaches**The authors would like to thank Huawei Canada Research Centre for financial & technical support.

There have been many recent advances in the Traffic Signal Control literature that use reinforcement learning, most of which is undertaken using the model-free approach. Approaches in the model-free domain, attempt to learn the value or the policy function directly without attempting to learn the environment transition dynamics. Therefore, training the value function under a specified dynamics fails to differentiate the value updates from the …