Tpgca
Transferable Policy Generation and Credit Assignment Network for Cooperative Multiagent Reinforcement Learning
Bibliographic Data
| ID | 22107454 |
|---|---|
| Authors | Wei Li (0000-0002-3581-849X, Southeast University), W J Li (Southeast University), Jiali Lv (0009-0003-2706-5613, Southeast University), Hongming Liu (0009-0002-4305-7309, Southeast University), Kaizhu Huang (0000-0002-3034-9639, Duke Kunshan University), Aiguo Song (0000-0002-1982-6780, Southeast University) |
| Year | 2026 |
| Volume | 13 |
| Issue | 2 |
| Pages | 2557-2571 |
| Publication date | 2026-04-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | IEEE Transactions on Computational Social Systems (JOURNAL) |
| Journal identifiers | ISSN: 2329-924X • E-ISSN: 2373-7476 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) (PUBLISHER) |
| DOI | 10.1109/tcss.2025.3628971 |
| OpenAlex | W7130348084 |
| Language | EN |
| References cited | 31 |
Multiagent reinforcement learning (MARL) methods have good application performances and prospects in cooperative tasks. To improve the capability of agent policy learning in new scenarios, some methods transfer the learned policy knowledge to new scenarios. However, most methods only focus on the knowledge transfer of individual agent policies, neglecting the credit assignment among agents in cooperative tasks, which results in a transfer bias of cooperative policies. In this paper, we propose a novel method, transferable policy generation and credit assignment (TPGCA) network for cooperative MARL. TPGCA can transfer the entire MARL model by the constructed transferable $Q$ -value network and mixing network. Specifically, in TPGCA, to enhance the effectivity and transferability of agent policies, we design the correspondence network between observations and actions (COA) on the basis of transformer and gated recurrent unit (GRU). To implement the reliable credit assignment and diminish the transfer bias, we devise the role-based joint $Q$ -value decomposition network (RVD) that can evaluate the contributions of agents from different observation perspectives. Experimental results in various micro-management scenarios on StarCraft multiagent challenge (SMAC) and multiagent particle environment (MPE) sufficiently demonstrate the effectiveness and transferability of TPGCA
Decomposition · Multi-agent system · Network topology · Reinforcement learning · Transfer of learning · Transferability · Domain Adaptation and Few-Shot Learning · Explainable Artificial Intelligence (XAI · Reinforcement Learning in Robotics
Emergence of Social Norms in Metanorms Game With High-Order Interaction Topology
Modeling and Simulating Adaptation Strategies Against Sea-Level Rise Using Multiagent Deep Reinforcement Learning
Collaborative Edge Computing for Social Internet of Vehicles to Alleviate Traffic Congestion
Priority Over Quantity
A Multiline Customized Bus Planning Method Based on Reinforcement Learning and Spatiotemporal Clustering Algorithm
Fairness-Aware Competitive Bidding Influence Maximization in Social Networks
| Highly cited | No |
|---|