Program Overview

Venue: SMU Administration Building

Level 4

Level 5

Note

Receipt Desk and Tea Break are located at Level 4 (Dec. 18) and Level 5 (Dec. 19 - Dec. 21)
Dec. 18 - Day 1 - Tutorials and Workshops
Date / Time Topic
9:00-10:15 Tutorial 1
Diffusion Models for Decision-Making Agents
(AESR 4-1)		 Workshop 1
Embodied AI
(AESR 4-2)
10:15-10:30 Coffee Break
10:30-12:00 Workshop 2
Game Theory
(AESR 4-1)		 Workshop 1
Embodied AI
(AESR 4-2)
12:00-13:30 Lunch Break
13:30-14:45 Tutorial 2
Causal Empowered Agents & Foundation Models
(AESR 4-1)		 Workshop 3
Open Environment Multi-agent Reinforcement Learning
(AESR 4-2)
14:45-15:00 Coffee Break
15:00-18:00 Workshop 4
LLM-based Code Agent
(AESR 4-1)		 Workshop 3
Open Environment Multi-agent Reinforcement Learning
(AESR 4-2)
Dec. 19 - Day 2 - AI Agent Day (Details)
Date / Time Topic
9:00-9:45 AI Agent Day Regular Session
(AMRA)
9:45-10:15 Coffee Break
10:15-12:15 AI Agent Day Regular Session
(AMRA)
12:15-13:30 Lunch Break
13:30-13:40 LLM Reasoning Forum Opening
(AMRA)
13:40-15:00 LLM Reasoning Forum
(AMRA)
15:00-15:20 Coffee Break
15:20-16:40 LLM Reasoning Forum
(AMRA)
16:40-17:30 Panel Discussion
(AMRA)
Dec. 20 - Day 3 - Main Conference
Date / Time Topic
9:00-9:20 Opening
(AMRA)
9:20-10:20 Keynote 1 - Decentralized Neural Networks
Richard S. Sutton
Chair: Bo An
(AMRA)
10:20-10:50 Coffee Break
10:50-12:30 Offline Learning and Trajectory Optimization
Chair: Lei Yuan
(AEMT)		 Deep Learning and Application
Chair: Lei Feng
(AESR 5-1)
12:30-13:30 Lunch Break
13:30-14:30 Keynote 2 - Foundations of Foundation Models
Shuicheng Yan
Chair: Yaodong Yang
(AMRA)
14:30-15:00 Coffee Break
15:00-16:20 MARL and Applications I
Chair: Tianpei Yang
(AEMT)		 MARL and Applications II
Chair: Youzhi Zhang
(AESR 5-1)
18:30-22:30 Banquet
Dec. 21 - Day 4 - Main Conference
Date / Time Topic
9:00-10:00 Keynote 3 - Robotic Foundation Models
Sergey Levine
Chair: Weinan Zhang
(AMRA)
10:00-10:30 Coffee Break
10:30-11:30 Game Theory and Mechanism Design I
Chair: Weiran Shen
(AEMT)		 Game Theory and Mechanism Design II
Chair: Wanyuan Wang (AESR 5-1)
11:30-13:00 Lunch Break
13:00-14:00 Keynote 4 - Multi-Agent Learning in Games
Georgios Piliouras
Chair: Yang Yu
(AMRA)
14:00-15:30 Single Agent RL and Application
Chair: Chao Yu
(AEMT)

Paper List

Session: Offline Learning and Trajectory Optimization

Chair: Lei Yuan

10:50-12:20, Dec. 20, 2024, UTC+8. Seminar Room: Level 5, AEMT.

  1. Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning (NeurIPS’24) 10:50-11:10
    Yang Dai, Oubo Ma, Longfei Zhang, Xingxing Liang, Shengchao Hu,
    Mengzhu Wang, Shouling Ji, Jincai Huang, Li Shen     Xingxing Liang
  2. InPTR: Integration Prioritized Trajectory Replay (DAI’24) 11:10-11:30
    Chendie Yao, Xingxing Liang, Longfei Zhang, Jincai Huang, Jun Lei, Yulong Zhang Chendie Yao
  3. Multi-Agent Trajectory Prediction with Scalable Diffusion Transformer (DAI’24) 11:30-11:50
    Shenyu Zhang, Shixiong Kai, Chang Chen, Yuzheng Zhuang,
    Zhengbang Zhu, Minghuan Liu, Weinan Zhang     Shenyu Zhang
  4. SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization (NeurIPS’24) 11:50-12:10
    Zixuan Chen, Ze Ji, Jing Huo, Yang Gao Zixuan Chen
  5. Towards Smaller and Faster GPTs (DAI’24 Student Poster) 12:10-12:15
    Sathya Krishnan Suresh, Shunmugapriya P Sathya Krishnan Suresh
  6. SOPPU: Scalable One PEFT per User (DAI’24 Student Poster) 12:15-12:20
    Yash Jain, Mohor Banerjee Yash Jain

Session: Deep Learning and Application

Chair: Lei Feng

10:50-12:30, Dec. 20, 2024, UTC+8. Seminar Room: Level 5, AESR 5-1.

  1. Factor Graph Neural Network Meets Max-Sum: A Real-Time Route Planning Algorithm for Massive-Scale Trips (AAMAS’24) 10:50-11:10
    Yixuan Li, Wanyuan Wang, Weiyi Xu, Yanchen Deng, Weiwei Wu Yixuan Li
  2. Moderate Message Passing Improves Calibration: A Universal Way to Mitigate Confidence Bias in Graph Neural Networks (AAAI’24) 11:10-11:30
    Min Wang, Hao Yang, Jincai Huang, Qing Cheng Jincai Huang
  3. State Abstraction via Deep Supervised Hash Learning (TNNLS’24) 11:30-11:50
    Guang Yang, Zheng Xu, Jing Huo, Shangdong Yang, Tianyu Ding, Xingguo Chen Guang Yang
  4. DAG-based Column Generation for Adversarial Team Games (ICML’24) 11:50-12:10
    Youzhi Zhang, Bo An, Daniel Dajun Zeng Youzhi Zhang
  5. Visual Whole-Body Control for Legged Loco-Manipulation (CoRL’24) 12:10-12:30
    Minghuan Liu, Zixuan Chen, Xuxin Cheng, Yandong Ji,
    Ri-Zhao Qiu, Ruihan Yang, Xiaolong Wang     Mingxuan Liu

Session: MARL and Applications I

Chair: Tianpei Yang

15:00-16:00, Dec. 20, 2024, UTC+8. Seminar Room: Level 5, AEMT.

  1. Variational Stochastic Games (DAI’24) 15:00-15:20
    Zhiyu Zhao, Haifeng Zhang Zhiyu Zhao
  2. Boosting Studies of Multi-Agent Reinforcement Learning on Google Research Football Environment: the Past, Present, and Future (AAMAS’24) 15:20-15:40
    Yan Song, He Jiang, Haifeng Zhang, Zheng Tian, Weinan Zhang, Jun Wang Yan Song
  3. TaxAI: A Dynamic Economic Simulator and Benchmark for Multi-Agent Reinforcement Learning (AAMAS’24) 15:40-16:00
    Qirui Mi, Siyu Xia, Yan Song, Haifeng Zhang, Shenghao Zhu, Jun Wang Qirui Mi

Session: MARL and Applications II

Chair: Youzhi Zhang

15:00-16:20, Dec. 20, 2024, UTC+8. Seminar Room: Level 5, AESR 5-1.

  1. Multi-agent Multi-game Entity Transformer: Towards Generalist Models in MARL (DAI’24) 15:00-15:20
    Rundong Wang, Weixuan Wang, Xianhan Zeng, Liang Wang, Zhengjie Lian, Yiming Gao, Feiyu Liu, Siqin Li,
    Xianliang Wang, Qiang Fu, Wei Yang, Lanxiao Huang, Longtao Zheng, Zinovi Rabinovich, Bo An     Rundong Wang
  2. Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs (ICML’24) 15:20-15:40
    Stelios Triantafyllou, Aleksa Sukovic, Debmalya Mandal, Goran Radanovic Stelios Triantafyllou
  3. A Comprehensive Evaluation Framework for Multi-Agent Reinforcement Learning (DAI’24) 15:40-16:00
    Zonglei Jing, Xiaojun Chang, Mingxuan Zhu, Simin Li, Aishan Liu, Xiaoqian Li, Xianglong Liu Zonglei Jing
  4. SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning. (NeurIPS’22) 16:00-16:20
    Jianhong Wang, Yuan Zhang, Yunjie Gu, Tae-Kyun Kim Jianhong Wang

Session: Game Theory and Mechanism Design I

Chair: Weiran Shen

10:30-11:30, Dec. 21, 2024, UTC+8. Seminar Room: Level 5, AEMT.

  1. A Game Theory Reward Model for Federated Learning with Probabilistic Verification (DAI’24) 10:30-10:50
    Gennaro Auricchio, Harry Clough, Christopher Ho, Kaigui Bian, Changyu Dong, Kan Yang, Jie Zhang Gennaro Auricchio
  2. Optimal Fixed-Price Mechanism with Signaling (DAI’24) 10:50-11:10
    Zhikang Fan, Weiran Shen Zhikang Fan
  3. RegFTRL: Efficient Equilibrium Learning in Two-Player Zero-Sum Games (DAI’24) 11:10-11:30
    Zijian Fang, Zongkai Liu, Chao Yu Zijian Fang

Session: Game Theory and Mechanism Design II

Chair: Wanyuan Wang

10:30-11:30, Dec. 21, 2024, UTC+8. Seminar Room: Level 5, AESR 5-1.

  1. Efficient and Scalable Reinforcement Learning for Large-scale Network Control (NMI’24) 10:30-10:50
    Chengdong Ma, Aming Li, Yali Du, Hao Dong, Yaodong Yang Chengdong Ma
  2. Opponent Modeling in Multiplayer Imperfect-Information Games (DAI’24) 10:50-11:10
    Sam Ganzfried, Kevin Wang, Max Chiswick Max Chiswick
  3. Safe and Robust Subgame Exploitation in Imperfect Information Games (ICML’24) 11:10-11:30
    Zhenxing Ge, Zheng Xu, Tianyu Ding, Linjian Meng, Bo An, Wenbin Li, Yang Gao Zhenxing Ge

Session: Single Agent RL and Application

Chair: Chao Yu

14:00-15:20, Dec. 21, 2024, UTC+8. Seminar Room: Level 5, AEMT.

  1. Adaptive Command: Real-Time Policy Adjustment via Language Models in StarCraft II (DAI’24) 14:00-14:20
    Weiyu Ma, Dongyu Xu, Shu Lin, Haifeng Zhang, Jun Wang Weiyu Ma
  2. Logarithmic Function Matters Policy Gradient Deep Reinforcement Learning (DAI’24) 14:20-14:40
    Qi Liu, Jingxiang Guo, Zhongjian Qiao, Pengbin Chen, Jinxuan Zhu, Yanjie Li Presenter: Qi Liu
  3. CoMoU: Model-based Dynamics Estimation for Efficient Offline-to-online Reinforcement Learning (DAI’24) 14:40-15:00
    Dongxiang Chen, Ying Wen Dongxiang Chen
  4. Looking Ahead to Avoid Being Late: Solving Hard-Constrained Traveling Salesman Problem (DAI’24) 15:00-15:20
    Jingxiao Chen, Ziqin Gong, Minghuan Liu, Jun Wang, Yong Yu, Weinan Zhang Jingxiao Chen