7 citations · 16 across the 19 of their papers we have counts for
20 papers
HiRE: Hindsight Reward Editing for Policy Finetuning
Haoyi Niu, Zhengtao Han, Yufeng Ji +2
Pre-trained robot policies always require finetuning to adapt to specific environments. Reinforcement Learning (RL) offers high performance potential because it improves action opt…
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
Dongxiu Liu, Haoyi Niu, Peng Cheng +5
In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are largely confined to discrete-time…
Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models
Yufeng Ji, Wenhao Tang, Haoyi Niu +3
Action supervision in vision-language-action (VLA) models is often treated as a downstream objective for learning action prediction. In this paper, we study it instead as a force t…
A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models
Yilin Wang, Shangzhe Li, Haoyi Niu +4
We are interested in solving the problem of imitation learning with a limited amount of real-world expert data. Existing offline imitation methods often struggle with poor data cov…
PhysiAgent: An Embodied Agent Framework in Physical World
Zhihao Wang, Jianxiong Li, Jinliang Zheng +6
Vision-Language-Action (VLA) models have achieved notable success but often struggle with limited generalizations. To address this, integrating generalized Vision-Language Models (…
Efficient Robotic Policy Learning via Latent Space Backward Planning
Dongxiu Liu, Haoyi Niu, Zhihao Wang +6
Current robotic planning methods often rely on predicting multi-frame images with full pixel details. While this fine-grained approach can serve as a generic world model, it introd…
Skill Expansion and Composition in Parameter Space
Tenglong Liu, Jianxiong Li, Yinan Zheng +4
Humans excel at reusing prior knowledge to address new challenges and developing skills while solving problems. This paradigm becomes increasingly popular in the development of aut…
Are Expressive Models Truly Necessary for Offline RL?
Guan Wang, Haoyi Niu, Jianxiong Li +3
Among various branches of offline reinforcement learning (RL) methods, goal-conditioned supervised learning (GCSL) has gained increasing popularity as it formulates the offline RL…
xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing
Haoyi Niu, Qimao Chen, Tenglong Liu +5
Reusing pre-collected data from different domains is an appealing solution for decision-making tasks, especially when data in the target domain are limited. Existing cross-domain p…
DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
Jianxiong Li, Jinliang Zheng, Yinan Zheng +9
Multimodal pretraining is an effective strategy for the trinity of goals of representation learning in autonomous robots: 1) extracting both local and global task progressions; 2)…
A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents
Haoyi Niu, Jianming Hu, Guyue Zhou +1
The burgeoning fields of robot learning and embodied AI have triggered an increasing demand for large quantities of data. However, collecting sufficient unbiased data from the targ…
Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Driving
Haoyi Niu, Qimao Chen, Yingyue Li +2
The deployment of autonomous vehicles (AVs) has faced hurdles due to the dominance of rare but critical corner cases within the long-tail distribution of driving scenarios, which n…
Continual Driving Policy Optimization with Closed-Loop Individualized Curricula
Haoyi Niu, Yizhou Xu, Xingjian Jiang +1
The safety of autonomous vehicles (AV) has been a long-standing top concern, stemming from the absence of rare and safety-critical scenarios in the long-tail naturalistic driving d…
H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps
Haoyi Niu, Tianying Ji, Bingqi Liu +7
Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online R…
(Re)H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learning
Haoyi Niu, Kun Ren, Yizhou Xu +4
Autonomous driving and its widespread adoption have long held tremendous promise. Nevertheless, without a trustworthy and thorough testing procedure, not only does the industry str…
Discriminator-Guided Model-Based Offline Imitation Learning
Wenjia Zhang, Haoran Xu, Haoyi Niu +5
Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from sev…
When to Trust Your Simulator: Dynamics-Aware Hybrid Offline-and-Online Reinforcement Learning
Haoyi Niu, Shubham Sharma, Yiwen Qiu +4
Learning effective reinforcement learning (RL) policies to solve real-world complex tasks can be quite challenging without a high-fidelity simulation environment. In most cases, we…
A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
Guan Wang, Haoyi Niu, Desheng Zhu +3
Heated debates continue over the best autonomous driving framework. The classic modular pipeline is widely adopted in the industry owing to its great interpretability and stability…
DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning
Haoyi Niu, Jianming Hu, Zheyu Cui +1
How to explore corner cases as efficiently and thoroughly as possible has long been one of the top concerns in the context of deep reinforcement learning (DeepRL) autonomous drivin…
Tactical Decision Making for Emergency Vehicles Based on A Combinational Learning Method
Haoyi Niu, Jianming Hu, Zheyu Cui +1
Increasing the response time of emergency vehicles(EVs) could lead to an immeasurable loss of property and life. On this account, tactical decision making for EVs' microscopic cont…