Adaptive Broad-Deep Reinforcement Learning for Intelligent Traffic Light Control

Deep reinforcement learning (DRL) has superior autonomous decision-making capabilities, combining deep learning and reinforcement learning. Unlike DRL employs deep neural networks, broad reinforcement learning (BRL) adopts the broad learning system (BLS) that is established with flat networks to generate the strategy. This paper proposes the multiagent adaptive broad-deep reinforcement learning (ABDRL) approach for traffic light control (TLC), which combines the broad network with the deep network structure. Specifically, the structure of ABDRL first expands in the form of flatted broad networks. Then the feature representation module that contains deep neural networks is employed to extract the critical traffic information. In addition, experiences sampled randomly by the experience replay mechanism cannot reflect the current training status of the agent effectively. In order to alleviate the impacts caused by random sampling, the forgetful experience mechanism is incorporated into ABDRL. The forgetful experience mechanism enables the agent to discriminate the importance of experiences stored in the experience reply buffer to improve robustness and adaptability. We validate the effectiveness of ABDRL in TLC, and the results illustrate the optimality and robustness of ABDRL over the state-of-the-art multiagent deep reinforcement learning (MADRL) algorithms.