contact me
Yi Wu's Personal Website
  • Home
  • Publications
  • Projects
  • Interests
  • Contact
My Google scholar page is here with the full list of papers including pre-prints.

Publications

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores (ICLR 2024)
Zhiyu Mei, Wei Fu, Jiaxuan Gao, Guangju Wang, Huanchen Zhang, Yi Wu

Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets  (ICLR 2024)
Yihuan Mao, Chengjie Wu, Xi Chen, Hao Hu, Ji Jiang, Tianze Zhou, Tangjie Lv, Changjie Fan, Zhipeng Hu, Yi Wu, Yujing Hu, Chongjie Zhang

OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control (RA-L)
Botian Xu, Feng Gao, Chao Yu, Ruize Zhang, Yi Wu, Yu Wang

Quarl: A Learning-Based Quantum Circuit Optimizer (OOPSLA 2024)
Zikun Li, Jinjun Peng, Yixuan Mei, Sina Lin, Yi Wu, Oded Padon, Zhihao Jia

LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination (AAMAS 2024)
Jijia Liu*, Chao Yu*, Jiaxuan Gao*, Yuqing Xie, Qingmin Liao, Yi Wu, Yu Wang
​
MESA: Cooperative Meta-Exploration in Multi-Agent Learning through Exploiting State-Action Space Structure (AAMAS 2024)
Zhicheng Zhang*, Yancheng Liang*, Yi Wu and Fei Fang

Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning (AAAI 2024)
Jiayu Chen*, Zelai Xu*, Yunfei Li, Chao Yu, Jiaming Song, Huazhong Yang, Fei Fang, Yu Wang, Yi Wu
​
Understanding Curriculum Learning in Policy Optimization for Online Combinatorial Optimization (TMLR)
Runlong Zhou, Zelin He, Yuandong Tian, Yi Wu, Simon Shaolei Du
​
Iteratively Learn Diverse Strategies with State Distance Information (NeurIPS 2023)
Wei Fu, Weihua Du, Jingwei Li, Sunli Chen, Jingzhao Zhang, Yi Wu

Automatics Truss Design with Reinforcement Learning (IJCAI 2023)
Weihua Du*, Jinglun Zhao*, Chao Yu, Xingcheng Yao, Zimeng Song, Siyang Wu, Ruifeng Luo, Zhiyuan Liu, Xianzhong Zhao, Yi Wu

autotruss.pdf
File Size: 1803 kb
File Type: pdf
Download File

Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased (ICLR 2023)
Chao Yu*, Jiaxuan Gao*, Weilin Liu, Botian Xu, Hao Tang, Jiaqi Yang, Yu Wang, Yi Wu
​
hsp.pdf
File Size: 1672 kb
File Type: pdf
Download File

SpeedyZero: Mastering Atari with Limited Data and Time (ICLR 2023)
Yixuan Mei*, Jiaxuan Gao*, Weirui Ye, Shaohuai Liu, Yang Gao, Yi Wu

speedyzero.pdf
File Size: 939 kb
File Type: pdf
Download File

Efficient Bimanual Handover and Rearrangement via Symmetry-Aware Actor-Critic Learning (ICRA 2023)
Yunfei Li*, Chaoyi Pan*, Huazhe Xu, Xiaolong Wang, Yi Wu

bimanual.pdf
File Size: 3973 kb
File Type: pdf
Download File

Fictitious Cross-Play: Learning Nash Equilibrium in Mixed Cooperative-Competitive Games (AAMAS 2023)
Zelai Xu, Yancheng Liang, Chao Yu, Yu Wang and Yi Wu

fxp.pdf
File Size: 3979 kb
File Type: pdf
Download File

Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration (AAMAS 2023)
Chao Yu*, Xinyi Yang*, Jiaxuan Gao*, Jiayu Chen, Yunfei Li, Jijia Liu, Yunfei Xiang, Ruixin Huang, Huazhong Yang, Yi Wu and Yu Wang

async-mappo.pdf
File Size: 7829 kb
File Type: pdf
Download File

Differentiable Arbitrating in Zero-sum Markov Games (AAMAS 2023)
Jing Wang*, Meichen Song*, Feng Gao*, Boyi Liu, Zhaoran Wang and Yi Wu

incent-rl.pdf
File Size: 1350 kb
File Type: pdf
Download File

Beyond Information Gain: An Empirical Benchmark for Low-Switching-Cost Reinforcement Learning (TMLR)
Shusheng Xu, Yancheng Liang, Yunfei Li, Simon Shaolei Du, Yi Wu
​
ls-rl.pdf
File Size: 10139 kb
File Type: pdf
Download File

Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination (AAAI 2023)
Rui Zhao, Jinming Song, Yufeng Yuan, Hu Haifeng, Yang Gao, Yi Wu, Zhongqian Sun, Yang Wei

The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games (NeurIPS 2022, benchmark track)
Chao Yu*, Akash Velu*, Eugene Vinitsky, Jiaxuan Gao, Yu Wang, Alexandre Bayen, Yi Wu
Check out the official MAPPO github repo and the (a bit dated) BAIR blog
mappo.pdf
File Size: 3154 kb
File Type: pdf
Download File

Grounded Reinforcement Learning: Learning to Win the Game under Human Commands (NeurIPS 2022)
Shusheng Xu, Huaijie Wang, Yi Wu
Check out the full version here and the videos at our project website.
grl.pdf
File Size: 1242 kb
File Type: pdf
Download File

Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning (NeurIPS 2022)
Zhecheng Yuan*, Zhengrong Xue*, Bo Yuan, Xueqian Wang, Yi Wu, Yang Gao, Huazhe Xu

pie-g.pdf
File Size: 6674 kb
File Type: pdf
Download File

Learning Efficient Multi-Agent Cooperative Visual Exploration (ECCV 2022)
Chao Yu*, Xinyi Yang*, Jiaxuan Gao*, Huazhong Yang, Yu Wang, Yi Wu
​Check out the appendix and the project website.
maans.pdf
File Size: 4124 kb
File Type: pdf
Download File

Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning (ICML 2022)
Yunfei Li*, Tian Gao*, Jiaqi Yang, Huazhe Xu, Yi Wu

pair.pdf
File Size: 5446 kb
File Type: pdf
Download File

Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (ICML 2022)
Wei Fu, Chao Yu, Zelai Xu, Jiaqi Yang, Yi Wu
Note: this version has been updated after ICML. Also check the latest BAIR blog and the arxiv version. 
pg-ar.pdf
File Size: 7662 kb
File Type: pdf
Download File

Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization (ICLR 2022)
Zihan Zhou*, Wei Fu*, Bingliang Zhang, Yi Wu
​Check out our code, full paper (with appendix) and discovered behaviors
rspo.pdf
File Size: 622 kb
File Type: pdf
Download File

Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets (ICRA 2022)
Yunfei Li, Tao Kong, Lei Li, Yi Wu

pmr.pdf
File Size: 5373 kb
File Type: pdf
Download File

Sequence Level Contrastive Learning for Text Summarization (AAAI 2022)
Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei

seqco.pdf
File Size: 342 kb
File Type: pdf
Download File

Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems (NeurIPS 2021)​
Jiayu Chen, Yuanxin Zhang, Yuanfan Xu, Huimin Ma, Huazhong Yang, Jiaming Song, Yu Wang, Yi Wu

vacl.pdf
File Size: 2664 kb
File Type: pdf
Download File

NovelD: A Simple yet Effective Exploration Criterion (NeurIPS 2021)
Tianjun Zhang, Huazhe Xu, Xiaolong Wang, Yi Wu, Kurt Keutzer, Joseph E. Gonzalez, Yuandong Tian
​
noveid.pdf
File Size: 2810 kb
File Type: pdf
Download File

Native Chinese Reader: A Dataset Towards Native-Level Chinese Machine Reading Comprehension (NeurIPS 2021, dataset track)
​Shusheng Xu*, Yichen Liu*, Xiaoyu Yi, Siyuan Zhou, Huizi Li, Yi Wu
Dataset, models and supplementary materials can be found at our project website
ncr.pdf
File Size: 1141 kb
File Type: pdf
Download File

Learning to Design and Construct Bridge without Blueprint (IROS 2021)
Yunfei Li, Tao Kong, Lei Li, Yifeng Li, Yi Wu

bridge.pdf
File Size: 6306 kb
File Type: pdf
Download File

Temporal Induced Self-Play for Stochastic Bayesian Games (IJCAI 2021)
Weizhe Chen*, Zihan Zhou*, Yi Wu, Fei Fang

tisp.pdf
File Size: 693 kb
File Type: pdf
Download File

Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization (ICLR 2021)
Zhenggang Tang*, Chao Yu*, Boyuan Chen, Huazhe Xu, Xiaolong Wang, Fei Fang, Simon Shaolei Du, Yu Wang, Yi Wu
​
rpg.pdf
File Size: 3542 kb
File Type: pdf
Download File

Solving Compositional Reinforcement Learning Problems via Task Reduction (ICLR 2021)
Yunfei Li, Yilin Wu, Huazhe Xu, Xiaolong Wang, Yi Wu
​
sir.pdf
File Size: 2363 kb
File Type: pdf
Download File

Multi-Task Reinforcement Learning with Soft Modularization (NeurIPS 2020)
​Ruihan Yang, Huazhe Xu, Yi Wu, Xiaolong Wang
softmod.pdf
File Size: 4005 kb
File Type: pdf
Download File

Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers (Findings of EMNLP 2020)
​Shusheng Xu, Xingxing Zhang, Yi Wu, Furu Wei, Ming Zhou
Source code can be found here
stas-emnlp.pdf
File Size: 788 kb
File Type: pdf
Download File

Emergent Tool Use  from Multi-Agent Autocurricula (ICLR 2020, Spotlight)
Bowen Baker*, Ingmar Kanitscheider*, Todor Markov*, Yi Wu*, Glenn Powell*, Bob McGrew*, Igor Mordatch* (*team project)
Check out our blog post with the most popular video ever in OpenAI's history :)
hide-seek.pdf
File Size: 8756 kb
File Type: pdf
Download File

Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning (ICLR 2020)
Qian Long*, Zihan Zhou*, Abhibav Gupta, Fei Fang, Yi Wu†, Xiaolong Wang† († equal advising)
Project website and source code can be found here
epc.pdf
File Size: 5571 kb
File Type: pdf
Download File

Influence-Based Multi-Agent Exploration (ICLR 2020, Spotlight)
Tonghan Wang*, Jianhao Wang*, Yi Wu, Chongjie Zhang
The full version with appendix can be found here
edit.pdf
File Size: 4465 kb
File Type: pdf
Download File

Bayesian Relational Memory for Semantic Visual Navigation (ICCV 2019)
Yi Wu, Yuxin Wu, Aviv Tamar, Stuart Russell, Georgia Gkioxari, Yuandong Tian
Supplementary materials are here
All the source code is here. We also developed a much faster and super memory efficient version of House3D environment
brm-iccv.pdf
File Size: 2107 kb
File Type: pdf
Download File

Robust Multi-Agent Reinforcement Learning via Minimax Deep Deterministic Policy Gradient (AAAI 2019, Oral)
Shihui Li, Yi Wu, Xinyue Cui, Honghua Dong, Fei Fang, Stuart Russell
Source code can be found here
m3ddpg.pdf
File Size: 432 kb
File Type: pdf
Download File

Deep Reinforcement Learning for Green Security Games with Real-Time Information (AAAI 2019, Oral)
Yufei Wang, Zheyuan Ryan Shi, Lantao Yu, Yi Wu, Rohit Singh, Lucas Joppa, Fei Fang​
​
rlforsg.pdf
File Size: 3289 kb
File Type: pdf
Download File

Meta-Learning MCMC Proposals (NIPS 2018)
Tongzhou Wang, Yi Wu, David Moore​, Stuart Russell
A short version was accepted as an oral talk at AutoML workshop,​ ICML 2017

Supplementary materials are here
meta-mcmc.pdf
File Size: 1338 kb
File Type: pdf
Download File

Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms (ICML 2018)
Yi Wu, Siddharth Srivastava, Nicholas Hay​, Simon S. Du, Stuart Russell
A short version was accepted at PPS workshop,​ POPL 2017
mtbn.pdf
File Size: 654 kb
File Type: pdf
Download File

Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (NIPS 2017)
Ryan Lowe*, Yi Wu*, Aviv Tamar, Jean Harb, Pieter Abbeel, Igor Mordatch (* equal contribution)
The OpenAI blog for this work is here
maddpg.pdf
File Size: 1337 kb
File Type: pdf
Download File

Adversarial Training for Relation Extraction (EMNLP 2017)
Yi Wu, David Bamman, Stuart Russell
Source code can be found here
AtNRE.pdf
File Size: 636 kb
File Type: pdf
Download File

A Nearly-Black-Box Online Algorithm for Joint Parameter and State Estimation in Temporal Models (AAAI 2017, Oral)
Yusuf B. Erol*, Yi Wu*, Lei Li, Stuart Russell (* equal contribution)
Supplementary materials are here
apf-aaai.pdf
File Size: 1239 kb
File Type: pdf
Download File

Value Iteration Network (NIPS 2016, ​Best Paper Award)
Aviv Tamar, Yi Wu, Garrett Thomas, Sergey Levine, Pieter Abbeel
vin-nips16.pdf
File Size: 688 kb
File Type: pdf
Download File

Swift: Compiled Inference for Probabilistic Programming Languages (IJCAI 2016)
Yi Wu, Lei Li, Stuart Russell, Rastislav Bodik
Project Webpage and Github Repo
​

swift-ijcai.pdf
File Size: 1459 kb
File Type: pdf
Download File

Understanding and Evaluating Sparse Linear Discriminant Analysis (AISTATS 2015, Oral)
Yi Wu, David Wipf, Jeong-Min Yun​
s-lda15.pdf
File Size: 338 kb
File Type: pdf
Download File

Dual Space Analysis of the Sparse Linear Model (NIPS2012)
David Wipf, Yi Wu
dual2012.pdf
File Size: 152 kb
File Type: pdf
Download File

Selected Workshop Papers

Building Generalizable Agents with a Realistic and Rich 3D Environment
(NIPS 2017 Deep Reinforcement Learning Symposium; ICLR 2018 Workshop Track)
Check the Github page of our House3D project
House3D.pdf
File Size: 1998 kb
File Type: pdf
Download File

BFiT: From Possible-World Semantics to Random-Evaluation Semantics in an Open Universe 
(NIPS 2014 workshop on Probabilistic Programming, spotlight)
BFiT.pdf
File Size: 115 kb
File Type: pdf
Download File

Thesis

On Building Generalizable Learning Agents
Fall 2019 at UC Berkeley
thesis.pdf
File Size: 8129 kb
File Type: pdf
Download File

Powered by Create your own unique website with customizable templates.