Zhuang Zhang

Ye Han, Lijun Zhang, Dejian Meng et al.

The exploration-exploitation trade-off constitutes one of the fundamental challenges in reinforcement learning (RL), which is exacerbated in multi-agent reinforcement learning (MARL) due to the exponential growth of joint state-action spaces. This paper proposes a topology-enhanced MARL (TPE-MARL) method for optimizing cooperative decision-making of connected and autonomous vehicles (CAVs) in mixed traffic. This work presents two primary contributions: First, we construct a game topology tensor for dynamic traffic flow, effectively compressing high-dimensional traffic state information and decrease the search space for MARL algorithms. Second, building upon the designed game topology tensor and using QMIX as the backbone RL algorithm, we establish a topology-enhanced MARL framework incorporating visit counts and agent mutual information. Extensive simulations across varying traffic densities and CAV penetration rates demonstrate the effectiveness of TPE-MARL. Evaluations encompassing training dynamics, exploration patterns, macroscopic traffic performance metrics, and microscopic vehicle behaviors reveal that TPE-MARL successfully balances exploration and exploitation. Consequently, it exhibits superior performance in terms of traffic efficiency, safety, decision smoothness, and task completion. Furthermore, the algorithm demonstrates decision-making rationality comparable to or exceeding that of human drivers in both mixed-autonomy and fully autonomous traffic scenarios. Code of our work is available at \href{https://github.com/leoPub/tpemarl}{https://github.com/leoPub/tpemarl}.

Ye Han, Lijun Zhang, Dejian Meng et al.

In multi-vehicle cooperative driving tasks involving high-frequency continuous control, traditional state-based reward functions suffer from the issue of vanishing reward differences. This phenomenon results in a low signal-to-noise ratio (SNR) for policy gradients, significantly hindering algorithm convergence and performance improvement. To address this challenge, this paper proposes a novel Hybrid Differential Reward (HDR) mechanism. We first theoretically elucidate how the temporal quasi-steady nature of traffic states and the physical proximity of actions lead to the failure of traditional reward signals. Building on this analysis, the HDR framework innovatively integrates two complementary components: (1) a Temporal Difference Reward (TRD) based on a global potential function, which utilizes the evolutionary trend of potential energy to ensure optimal policy invariance and consistency with long-term objectives; and (2) an Action Gradient Reward (ARG), which directly measures the marginal utility of actions to provide a local guidance signal with a high SNR. Furthermore, we formulate the cooperative driving problem as a Multi-Agent Partially Observable Markov Game (POMDPG) with a time-varying agent set and provide a complete instantiation scheme for HDR within this framework. Extensive experiments conducted using both online planning (MCTS) and Multi-Agent Reinforcement Learning (QMIX, MAPPO, MADDPG) algorithms demonstrate that the HDR mechanism significantly improves convergence speed and policy stability. The results confirm that HDR guides agents to learn high-quality cooperative policies that effectively balance traffic efficiency and safety.