62 citations · 240 across the 26 of their papers we have counts for
27 papers
Growing and Transferring Pathways for LLM Reinforcement Learning
Haolin Tian, Yikang Li, Tonghan Wang
Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires considerable resources. Reusing th…
The Memory Curse: How Expanded Recall Erodes Cooperative Intent in LLM Agents
Jiayuan Liu, Tianqin Li, Shiyi Du +7
Context window expansion is often treated as a straightforward capability upgrade for LLMs, but we find it systematically fails in multi-agent social dilemmas. Across 7 LLMs and 4…
BundleFlow: Deep Menus for Combinatorial Auctions by Diffusion-Based Optimization
Tonghan Wang, Yanchen Jiang, David C. Parkes
Differentiable economics -- the use of deep learning for auction design -- has driven progress in the automated design of multi-item auctions with additive or unit-demand valuation…
On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow
Tonghan Wang, Heng Dong, Yanchen Jiang +2
Multiagent systems grapple with partial observability (PO), and the decentralized POMDP (Dec-POMDP) model highlights the fundamental nature of this challenge. Whereas recent approa…
The Bandit Whisperer: Communication Learning for Restless Bandits
Yunfan Zhao, Tonghan Wang, Dheeraj Nagaraj +2
Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynam…
Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts
Dima Ivanov, Paul Dütting, Inbal Talgam-Cohen +2
The increasing deployment of AI is shaping the future landscape of the internet, which is set to become an integrated ecosystem of AI agents. Orchestrating the interaction among AI…
GemNet: Menu-Based, Strategy-Proof Multi-Bidder Auctions Through Deep Learning
Tonghan Wang, Yanchen Jiang, David C. Parkes
Automated mechanism design (AMD) uses computational methods for mechanism design. Differentiable economics is a form of AMD that uses deep learning to learn mechanism designs and h…
Social Environment Design
Edwin Zhang, Sadie Zhao, Tonghan Wang +6
Artificial Intelligence (AI) holds promise as a technology that can be used to improve government and economic policy-making. This paper proposes a new research agenda towards this…
Multi-Sender Persuasion: A Computational Perspective
Safwan Hossain, Tonghan Wang, Tao Lin +3
We consider the multi-sender persuasion problem: multiple players with informational advantage signal to convince a single self-interested actor to take certain actions. This probl…
Never Explore Repeatedly in Multi-Agent Reinforcement Learning
Chenghao Li, Tonghan Wang, Chongjie Zhang +1
In the realm of multi-agent reinforcement learning, intrinsic motivations have emerged as a pivotal tool for exploration. While the computation of many intrinsic rewards relies on…
Deep Contract Design via Discontinuous Networks
Tonghan Wang, Paul Dütting, Dmitry Ivanov +2
Contract design involves a principal who establishes contractual agreements about payments for outcomes that arise from the actions of an agent. In this paper, we initiate the stud…
Symmetry-Aware Robot Design with Structured Subgroups
Heng Dong, Junyu Zhang, Tonghan Wang +1
Robot design aims at learning to create robots that can be easily controlled and perform tasks efficiently. Previous works on robot design have proven its ability to generate robot…
Non-Linear Coordination Graphs
Yipeng Kang, Tonghan Wang, Xiaoran Wu +2
Value decomposition multi-agent reinforcement learning methods learn the global value function as a mixing of each agent's individual utility functions. Coordination graphs (CGs) r…
Low-Rank Modular Reinforcement Learning via Muscle Synergy
Heng Dong, Tonghan Wang, Jiayuan Liu +1
Modular Reinforcement Learning (RL) decentralizes the control of multi-joint robots by learning policies for each actuator. Previous work on modular RL has proven its ability to co…
Multi-Agent Policy Transfer via Task Relationship Modeling
Rongjun Qin, Feng Chen, Tonghan Wang +5
Team adaptation to new cooperative tasks is a hallmark of human intelligence, which has yet to be fully realized in learning agents. Previous work on multi-agent transfer learning…
Self-Organized Polynomial-Time Coordination Graphs
Qianlan Yang, Weijun Dong, Zhizhou Ren +3
Coordination graph is a promising approach to model agent collaboration in multi-agent reinforcement learning. It conducts a graph-based value factorization and induces explicit co…
Containerized Distributed Value-Based Multi-Agent Reinforcement Learning
Siyang Wu, Tonghan Wang, Chenghao Li +2
Multi-agent reinforcement learning tasks put a high demand on the volume of training samples. Different from its single-agent counterpart, distributed value-based multi-agent reinf…
Context-Aware Sparse Deep Coordination Graphs
Tonghan Wang, Liang Zeng, Weijun Dong +3
Learning sparse coordination graphs adaptive to the coordination dynamics among agents is a long-standing problem in cooperative multi-agent learning. This paper studies this probl…
Celebrating Diversity in Shared Multi-Agent Reinforcement Learning
Chenghao Li, Tonghan Wang, Chengjie Wu +3
Recently, deep multi-agent reinforcement learning (MARL) has shown the promise to solve complex cooperative tasks. Its success is partly because of parameter sharing among agents.…
Birds of a Feather Flock Together: A Close Look at Cooperation Emergence via Multi-Agent RL
Heng Dong, Tonghan Wang, Jiayuan Liu +2
How cooperation emerges is a long-standing and interdisciplinary problem. Game-theoretical studies on social dilemmas reveal that altruistic incentives are critical to the emergenc…
RODE: Learning Roles to Decompose Multi-Agent Tasks
Tonghan Wang, Tarun Gupta, Anuj Mahajan +3
Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discove…
Off-Policy Multi-Agent Decomposed Policy Gradients
Yihan Wang, Beining Han, Tonghan Wang +2
Multi-agent policy gradient (MAPG) methods recently witness vigorous progress. However, there is a significant performance discrepancy between MAPG methods and state-of-the-art mul…
Incorporating Pragmatic Reasoning Communication into Emergent Language
Yipeng Kang, Tonghan Wang, Gerard de Melo
Emergentism and pragmatics are two research fields that study the dynamics of linguistic communication along substantially different timescales and intelligence levels. From the pe…
ROMA: Multi-Agent Reinforcement Learning with Emergent Roles
Tonghan Wang, Heng Dong, Victor Lesser +1
The role concept provides a useful tool to design and understand complex multi-agent systems, which allows agents with a similar role to share similar behaviors. However, existing…