Author name cluster

Kexing Peng

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

TIST Journal 2026 Journal Article

ROIS: Role-Based Multi-Agent Collaboration by Context-Time-Aware Information Sharing

Hanwen Qi
Tinghuai Ma
Kexing Peng
Xin Yu

In complex cooperative tasks, Multi-Agent Reinforcement Learning (MARL) faces the dual challenges of an exponentially growing joint action space and the constraints of partial observability. While the Centralized Training with Decentralized Execution (CTDE) paradigm is widely adopted, it often leads to homogeneous policies that lack the necessary specialization for complex teamwork. While role-based methods encourage specialization, they often lack mechanisms for inter-agent interaction. Consequently, the lack of rich information for role assignment means their roles may be assigned ineffectively, hindering the convergence of the team policy to its optimum. To address this critical gap, we propose ROIS, a novel framework that enhances multi-agent collaboration by grounding dynamic role assignments in a context-time-aware information sharing mechanism. Our key insight is to leverage a dedicated information sharing module that captures multi-step temporal context, providing each agent with richer, tailored feedback from its teammates. This mechanism directly addresses the lack of inter-agent interaction, leading to more accurate and effective role assignments. This results in a more coherent task division, which guides specialized policies toward the optimal joint policy and drastically reduces ineffective exploration. We conduct extensive experiments on the demanding StarCraft II, SMACv2, and Multi-agent Particle Environment benchmarks. The results demonstrate that ROIS consistently achieves state-of-the-art performance, significantly outperforming a wide range of advanced baselines, particularly in scenarios requiring deep coordination and policy adaptation. Finally, comprehensive ablation studies confirm the essential contribution of each component to the framework’s success.

Details DOI

AAMAS Conference 2025 Conference Paper

Enhancing Graph-based Coordination with Evolutionary Algorithms for Episodic Multi-agent Reinforcement Learning

Kexing Peng
Pengyi Li
Jianye Hao

Multi-agent Reinforcement Learning (MARL) has made significant progress in addressing coordination problems, but two key challenges persist in environments with partial observability: limited exploration and inaccurate evaluation of individual agents. To address these challenges, we propose a novel MARL framework that integrates Evolutionary Algorithms (EAs), episodic learning, and curiosity-driven exploration to optimize the coordination of joint policies using graph-based methods, named EECG. EAs are employed for their global optimization capabilities, particularly through population diversity and a gradient-free search mechanism, to enhance policy exploration. Initially, multiple agent teams explore and learn independently while sharing a common experience pool to enable data diversity. During the evolution phase, new joint policies are generated through crossover, mutation, and pareto-based selection. During the RL phase, diverse data is used to model and update the relationships among agents via Graph Neural Networks (GNNs), which help evaluate the effectiveness of individual agents’ behaviors. GNNs treat agents as nodes and their interactions as edges, capturing coordination relationships effectively while dynamically assigning representations to nodes and edges. Furthermore, curiosity-based exploration motivates teams to discover new states, while a memory system stores high-reward experiences. We evaluated EECG on several benchmarks, including StarCraft II, SUMO autonomous driving, and the Multi-Agent Particle Environment. Our empirical results show that EECG consistently outperforms current baselines, with its components significantly contributing to faster convergence, especially by improving exploration and agent coordination. Our code is available: https: //github. com/MercyM/EECG.

PDF

TIST Journal 2025 Journal Article

STPE-MARL: Spatio-Temporal Multi-Agent Population Evolution Reinforcement Learning

Kexing Peng
Shihao Zhu
Tinghuai Ma

Achieving joint goals efficiently in complex real-world tasks demands effective collaboration among multiple agents. Multi-Agent Reinforcement Learning (MARL) faces two interrelated challenges: limited exploration leads to early convergence on suboptimal behaviors, which in turn exacerbates non-stationarity under partial observability. To address these issues, we propose a novel framework, Spatio-Temporal Multi-agent Population Evolution (STPE-MARL). By integrating Evolutionary Algorithms (EAs) with MARL, our method enhances exploration diversity and facilitates global policy optimization. We further incorporate Graph Neural Networks (GNNs) to mitigate partial observability by encoding permutation symmetry through graph-based message passing. Two GNN-based training modes, Graph Relation and Graph Decomposition, are introduced to extend agents’ receptive fields and capture spatio-temporal dependencies through time-series trajectory sampling. We evaluate STPE-MARL in two complex environments: micromanagement tasks in StarCraft II and large-scale traffic simulations in SUMO (Simulation of Urban MObility). Experimental results demonstrate that STPE-MARL significantly improves policy convergence and outperforms baseline methods, highlighting the complementary roles of EAs in exploration and GNNs in addressing observation limitations.

Details DOI