Sotabase

Career

· Assistant Professor, Tsinghua University2026–
· PhD Student, Harvard University2021–2026
· Graduate Student, Tsinghua University2018–2021

Publications (64)

ROMA: Multi-Agent Reinforcement Learning with Emergent Roles
International Conference on Machine Learning · 2020
273
cited
RODE: Learning Roles to Decompose Multi-Agent Tasks
International Conference on Learning Representations · 2020
259
cited
Off-Policy Multi-Agent Decomposed Policy Gradients
International Conference on Learning Representations · 2020
203
cited
Celebrating Diversity in Shared Multi-Agent Reinforcement Learning
Neural Information Processing Systems · 2021
181
cited
Learning Nearly Decomposable Value Functions Via Communication Minimization
International Conference on Learning Representations · 2019
163
cited
Influence-Based Multi-Agent Exploration
International Conference on Learning Representations · 2019
150
cited
Context-Aware Sparse Deep Coordination Graphs
2021
37
cited
Multi-agent policy transfer via task relationship modeling
Science China Information Sciences · 2022
31
cited
Incorporating Pragmatic Reasoning Communication into Emergent Language
Neural Information Processing Systems · 2020
23
cited
Low-Rank Modular Reinforcement Learning via Muscle Synergy
Neural Information Processing Systems · 2022
21
cited
Deep Contract Design via Discontinuous Networks
Neural Information Processing Systems · 2023
18
cited
GemNet: Menu-Based, Strategy-Proof Multi-Bidder Auctions Through Deep Learning
ACM Conference on Economics and Computation · 2024
18
cited
Self-Organized Polynomial-Time Coordination Graphs
International Conference on Machine Learning · 2021
18
cited
Symmetry-Aware Robot Design with Structured Subgroups
International Conference on Machine Learning · 2023
18
cited
Multi-Sender Persuasion: A Computational Perspective
International Conference on Machine Learning · 2024
14
cited
Convergence of Multi-Agent Learning with a Finite Step Size in General-Sum Games
Adaptive Agents and Multi-Agent Systems · 2019
13
cited
Principal-Agent Reinforcement Learning: Orchestrating AI Agents with Contracts
2024
12
cited
Birds of a Feather Flock Together: A Close Look at Cooperation Emergence via Multi-Agent RL
arXiv.org · 2021
10
cited
Non-Linear Coordination Graphs
Neural Information Processing Systems · 2022
10
cited
The Bandit Whisperer: Communication Learning for Restless Bandits
AAAI Conference on Artificial Intelligence · 2024
7
cited
Sotabase
Tonghan Wang | Researcher Profile | Sotabase | Sotabase