THU-IDM

arXiv 2025 Robust Adaptation

Model Predictive Task Sampling for Efficient and Robust Adaptation

Authors: Qi (Cheems) Wang, Zehao Xiao, Yixiu Mao, Yun Qu, Jiayi Shen, Yiqin Lv, Xiangyang Ji

Paper Code

KDD 2025 Robust Adaptation

Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation

Authors: Cheems Wang, Yiqin Lv, Yixiu Mao, Yun Qu, Yi Xu, Xiangyang Ji

Paper

ICLR 2025

DynaPrompt: Dynamic Test-Time Prompt Tuning

Authors: Zehao Xiao, Shilin Yan, Jack Hong, Jiayin Cai, Xiaolong Jiang, Yao Hu, Jiayi Shen, Qi Wang, Cees G. M. Snoek

Paper

AAAI 2025 LLM4RL

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning

Authors: Yun Qu, Yuhang Jiang, Boyuan Wang, Yixiu Mao, Cheems Wang, Chang Liu, Xiangyang Ji

Paper Code

ICML 2024 LLM4RL

LLM-Empowered State Representation for Reinforcement Learning

Authors: Boyuan Wang, Yun Qu, Yuhang Jiang, Jianzhun Shao, Chang Liu, Wenming Yang, Xiangyang Ji

Paper Code Demo

NeurIPS 2024 Offline RL

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression

Authors: Yixiu Mao, Qi Wang, Chen Chen, Yun Qu, Xiangyang Ji

Paper

NeurIPS 2024 Robust Adaptation

Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning

Authors: Yiqin Lv, Qi Wang, Dong Liang, Zheng Xie

Paper

NeurIPS 2024 Multi-Task Learning

GO4Align: Group Optimization for Multi-Task Alignment

Authors: Jiayi Shen, Qi (Cheems) Wang, Zehao Xiao, Nanne Van Noord, Marcel Worring

Paper Code

ICML 2024

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation

Authors: Yuchen Yang, Yingdong Shi, Cheems Wang, Xiantong Zhen, Yuxuan Shi, Jun Xu

Paper Code

arXiv 2024 LLM4RL

Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration

Authors: Yun Qu, Boyuan Wang, Yuhang Jiang, Jianzhun Shao, Yixiu Mao, Cheems Wang, Chang Liu, Xiangyang Ji

Paper

NeurIPS 2024 Offline RL

Doubly Mild Generalization for Offline Reinforcement Learning

Authors: Yixiu Mao, Qi Wang, Yun Qu, Yuhang Jiang, Xiangyang Ji

Paper Code

ICLR 2023

Bridge the Inference Gaps of Neural Processes via Expectation Maximization

Authors: Qi Wang, Marco Federici, Herke van Hoof

Paper Code

NeurIPS 2023 Multi-Task Learning

Episodic Multi-Task Learning with Heterogeneous Neural Processes

Authors: Jiayi Shen, Xiantong Zhen, Qi Wang, Marcel Worring

Paper

The Innovation 2023

Large-scale generative simulation artificial intelligence: The next hotspot

Authors: Qi Wang, Yanghe Feng, Jincai Huang, Yiqin Lv, Zheng Xie, Xiaoshan Gao

Paper

NeurIPS 2023 Robust Adaptation

A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm

Authors: Qi Wang, Yiqin Lv, Yanghe Feng, Zheng Xie, Jincai Huang

Paper

ICML 2023 Offline RL

Supported Trust Region Optimization for Offline Reinforcement Learning

Authors: Yixiu Mao, Hongchang Zhang, Chen Chen, Yi Xu, Xiangyang Ji

Paper Code

NeurIPS 2023 Offline RL

Supported Value Regularization for Offline Reinforcement Learning

Authors: Yixiu Mao, Hongchang Zhang, Chen Chen, Yi Xu, Xiangyang Ji

Paper Code

AAAI 2023 Offline RL

DARL: distance-aware uncertainty estimation for offline reinforcement learning

Authors: Hongchang Zhang, Jianzhun Shao, Shuncheng He, Yuhang Jiang, Xiangyang Ji

Paper

ICLR 2023 Offline RL

In-sample Actor Critic for Offline Reinforcement Learning

Authors: Hongchang Zhang, Yixiu Mao, Boyuan Wang, Shuncheng He, Yi Xu, Xiangyang Ji

Paper

ICLR 2023 Offline RL

Pessimistic Policy Iteration for Offline Reinforcement Learning

Authors: Hongchang Zhang, Boyuan Wang, Yixiu Mao, Jianzhun Shao, Yuhang Jiang, Yi Xu, Xiangyang Ji

Paper

NeurIPS 2023 Offline RL

Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning

Authors: Jianzhun Shao, Yun Qu, Chen Chen, Hongchang Zhang, Xiangyang Ji

Paper Code

ICML 2023 MARL

Complementary Attention for Multi-Agent Reinforcement Learning

Authors: Jianzhun Shao, Hongchang Zhang, Yun Qu, Chang Liu, Shuncheng He, Yuhang Jiang, Xiangyang Ji

Paper Code

NeurIPS 2023 Offline RL

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

Authors: Yun Qu, Boyuan Wang, Jianzhun Shao, Yuhang Jiang, Chen Chen, Zhenbin Ye, Lin Liu, Junfeng Yang, Lin Lai, Hongyang Qin, Minwen Deng, Juchao Zhuo, Deheng Ye, Qiang Fu, Wei Yang, Guang Yang, Lanxiao Huang, Xiangyang Ji

Paper Code

ICLR 2023 MARL

Consciousness-Aware Multi-Agent Reinforcement Learning

Authors: Jianzhun Shao, Hongchang Zhang, Yun Qu, Chang Liu, Shuncheng He, Yuhang Jiang, Xiangyang Ji

Paper Code

ICML 2022 Meta-RL

Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search

Authors: Qi Wang, Herke van Hoof

Paper

NeurIPS 2022

Learning Expressive Meta-Representations with Mixture of Expert Neural Processes

Authors: Qi Wang, Herke van Hoof

Paper

AAAI 2022 Offline RL

State deviation correction for offline reinforcement learning

Authors: Hongchang Zhang, Jianzhun Shao, Yuhang Jiang, Shuncheng He, Guanwen Zhang, Xiangyang Ji

Paper

AAAI 2022 Unsupervised RL

Wasserstein unsupervised reinforcement learning

Authors: Shuncheng He, Yuhang Jiang, Hongchang Zhang, Jianzhun Shao, Xiangyang Ji

Paper

NeurIPS 2022 Unsupervised RL

Spd: Synergy pattern diversifying oriented unsupervised multi-agent reinforcement learning

Authors: Yuhang Jiang, Jianzhun Shao, Shuncheng He, Hongchang Zhang, Xiangyang Ji

Paper Code

COLT 2022 RL Theory

Horizon-free reinforcement learning in polynomial time: the power of stationary policies

Authors: Zihan Zhang, Xiangyang Ji, Simon Du

Paper

NeurIPS 2022 RL Theory

Near-optimal regret bounds for multi-batch reinforcement learning

Authors: Zihan Zhang, Yuhang Jiang, Yuan Zhou, Xiangyang Ji

Paper

COLT 2021 RL Theory

Is reinforcement learning more difficult than bandits? a near-optimal algorithm escaping the curse of horizon

Authors: Zihan Zhang, Xiangyang Ji, Simon Du

Paper

NeurIPS 2021 RL Theory

Improved variance-aware confidence sets for linear bandits and linear mixture mdp

Authors: Zihan Zhang, Jiaqi Yang, Xiangyang Ji, Simon S Du

Paper

ICML 2021 RL Theory

Near optimal reward-free reinforcement learning

Authors: Zihan Zhang, Simon Du, Xiangyang Ji

Paper

ICML 2021 RL Theory

Model-free reinforcement learning: from clipped pseudo-regret to sample complexity

Authors: Zihan Zhang, Yuan Zhou, Xiangyang Ji

Paper

ICML 2020

Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables

Authors: Qi Wang, Herke van Hoof

Paper Code

CVPR 2020

Pfrl: Pose-free reinforcement learning for 6d pose estimation

Authors: Jianzhun Shao, Yuhang Jiang, Gu Wang, Zhigang Li, Xiangyang Ji

Paper

NeurIPS 2020 RL Theory

Almost optimal model-free reinforcement learningvia reference-advantage decomposition

Authors: Zihan Zhang, Yuan Zhou, Xiangyang Ji

Paper

NeurIPS 2019 RL Theory

Regret minimization for reinforcement learning by evaluating the optimal bias function

Authors: Zihan Zhang, Xiangyang Ji

Paper

Introduction

News

Publications

Model Predictive Task Sampling for Efficient and Robust Adaptation

Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation

DynaPrompt: Dynamic Test-Time Prompt Tuning

Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning

LLM-Empowered State Representation for Reinforcement Learning

Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression

Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning

GO4Align: Group Optimization for Multi-Task Alignment

Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation

Choices are More Important than Efforts: LLM Enables Efficient Multi-Agent Exploration

Doubly Mild Generalization for Offline Reinforcement Learning

Bridge the Inference Gaps of Neural Processes via Expectation Maximization

Episodic Multi-Task Learning with Heterogeneous Neural Processes

Large-scale generative simulation artificial intelligence: The next hotspot

A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm

Supported Trust Region Optimization for Offline Reinforcement Learning

Supported Value Regularization for Offline Reinforcement Learning

DARL: distance-aware uncertainty estimation for offline reinforcement learning

In-sample Actor Critic for Offline Reinforcement Learning

Pessimistic Policy Iteration for Offline Reinforcement Learning

Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning

Complementary Attention for Multi-Agent Reinforcement Learning

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

Consciousness-Aware Multi-Agent Reinforcement Learning

Model-based Meta Reinforcement Learning using Graph Structured Surrogate Models and Amortized Policy Search

Learning Expressive Meta-Representations with Mixture of Expert Neural Processes

State deviation correction for offline reinforcement learning

Wasserstein unsupervised reinforcement learning

Spd: Synergy pattern diversifying oriented unsupervised multi-agent reinforcement learning

Horizon-free reinforcement learning in polynomial time: the power of stationary policies

Near-optimal regret bounds for multi-batch reinforcement learning

Is reinforcement learning more difficult than bandits? a near-optimal algorithm escaping the curse of horizon

Improved variance-aware confidence sets for linear bandits and linear mixture mdp

Near optimal reward-free reinforcement learning

Model-free reinforcement learning: from clipped pseudo-regret to sample complexity

Doubly Stochastic Variational Inference for Neural Processes with Hierarchical Latent Variables

Pfrl: Pose-free reinforcement learning for 6d pose estimation

Almost optimal model-free reinforcement learningvia reference-advantage decomposition

Regret minimization for reinforcement learning by evaluating the optimal bias function

Blogs

Team Members

Qi (Cheems) Wang

Zixuan Zhang

Boyuan Wang

Yun Qu

Yixiu Mao

Yuhang Jiang

Mengge Liu

Jinghao Chen

Wendong Huang

Wutong Xu

Zhenchan Su

Jianzhun Shao

Hongchang Zhang

Zihan Zhang

Shuncheng He