Independent reinforcement learning for weakly cooperative multiagent traffic control problem

• Main Authors: ZHANG, Chengwei, JIN, Shan, XUE, Wanli, XIE, Xiaofei, CHEN, Shengyong, CHEN, Rong
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Multiagent learning; Independent reinforcement learning; Cooperative Markov game; Traffic signal control; OS and Networks; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7052; https://ink.library.smu.edu.sg/context/sis_research/article/8055/viewcontent/2104.10917.pdf
• Institution: Singapore Management University

The adaptive traffic signal control (ATSC) problem can be modeled as a multiagent cooperative game among urban intersections, where intersections cooperate to counter the city's traffic conditions. Recently, reinforcement learning (RL) has achieved marked successes in managing sequential decision making problems, which motivates us to apply RL in the ATSC problem. One of the largest challenges of this problem is that the observation of intersection is typically partially observable, which limits the learning performance of RL algorithms. Considering the large scale of intersections in an urban traffic environment, we use independent RL to solve ATSC problem in this study. We model ATSC problem as a partially observable weak cooperative traffic model (PO-WCTM). Different from a traditional IRL task that averages the returns of all agents in fully cooperative games, the learning goal of each intersection in PO-WCTM is to reduce the cooperative difficulty of learning, which is also consistent with the traffic environment hypothesis. To achieve the optimal cooperative strategy of PO-WCTM, we propose an IRL algorithm called Cooperative Important Lenient Double DQN (CIL-DDQN), which extends Double DQN (DDQN) algorithm using two mechanisms: the forgetful experience mechanism and the lenient weight training mechanism. The former mechanism decreases the importance of experiences stored in the experience reply buffers, while the latter mechanism increases the weight experiences with high estimation and 'leniently' trains the DDQN neural network. Experiments in two real traffic scenarios and one simulated traffic scenarios show that, CIL-DDQN outperforms other methods in almost all performance indicators of ATSC.