Learning traffic signal control from demonstrations

Reinforcement learning (RL) has recently become a promising approach in various decision-making tasks. Among them, traffic signal control is the one where RL makes a great breakthrough. However, these methods always suffer from the prominent exploration problem and even fail to converge. To resolve this issue, we make an analogy between agents and humans. Agents can learn from demonstrations generated by traditional traffic signal control methods, in the similar way as people master a skill from expert knowledge. Therefore, we propose DemoLight, for the first time, to leverage demonstrations collected from classic methods to accelerate learning. Based on the state-of-the-art deep RL method Advantage Actor-Critic (A2C), training with demos are carried out for both the actor and the critic and reinforcement learning is followed for further improvement. Results under real-world datasets show that DemoLight enables a more efficient exploration and outperforms existing baselines with faster convergence and better performance.