Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Zihan Ding

Zihan Ding

Not Only Domain Randomization: Universal Policy with Embedding System Identification


Sep 28, 2021
Zihan Ding

Figure 1 for Not Only Domain Randomization: Universal Policy with Embedding System Identification
Figure 2 for Not Only Domain Randomization: Universal Policy with Embedding System Identification
Figure 3 for Not Only Domain Randomization: Universal Policy with Embedding System Identification
Figure 4 for Not Only Domain Randomization: Universal Policy with Embedding System Identification

  Access Paper or Ask Questions

Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation


May 14, 2021
Tianrui Hui, Shaofei Huang, Si Liu, Zihan Ding, Guanbin Li, Wenguan Wang, Jizhong Han, Fei Wang

Figure 1 for Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
Figure 2 for Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
Figure 3 for Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
Figure 4 for Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation
* Accepted by CVPR 2021 
  Access Paper or Ask Questions

Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning


Apr 19, 2021
Jie Ren, Yewen Li, Zihan Ding, Wei Pan, Hao Dong

Figure 1 for Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning
Figure 2 for Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning
Figure 3 for Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning
Figure 4 for Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning

  Access Paper or Ask Questions

Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos


Mar 07, 2021
Haoqi Yuan, Ruihai Wu, Andrew Zhao, Haipeng Zhang, Zihan Ding, Hao Dong

Figure 1 for Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
Figure 2 for Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
Figure 3 for Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos
Figure 4 for Robotic Visuomotor Control with Unsupervised Forward Model Learned from Videos

  Access Paper or Ask Questions

Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory


Feb 28, 2021
Zihan Ding, Ya-Yen Tsai, Wang Wei Lee, Bidan Huang

Figure 1 for Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory
Figure 2 for Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory
Figure 3 for Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory
Figure 4 for Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensory

  Access Paper or Ask Questions

DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration


Feb 23, 2021
Ya-Yen Tsai, Hui Xu, Zihan Ding, Chong Zhang, Edward Johns, Bidan Huang

Figure 1 for DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration
Figure 2 for DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration
Figure 3 for DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration
Figure 4 for DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration
* paper accepted and to be published in RA-L 2021 
  Access Paper or Ask Questions

DROID: Minimizing the Reality Gap usingSingle-Shot Human Demonstration


Feb 22, 2021
Ya-Yen Tsai, Hui Xu, Zihan Ding, Chong Zhang, Edward Johns, Bidan Huang

Figure 1 for DROID: Minimizing the Reality Gap usingSingle-Shot Human Demonstration
Figure 2 for DROID: Minimizing the Reality Gap usingSingle-Shot Human Demonstration
Figure 3 for DROID: Minimizing the Reality Gap usingSingle-Shot Human Demonstration
Figure 4 for DROID: Minimizing the Reality Gap usingSingle-Shot Human Demonstration

  Access Paper or Ask Questions

CDT: Cascading Decision Trees for Explainable Reinforcement Learning


Nov 15, 2020
Zihan Ding, Pablo Hernandez-Leal, Gavin Weiguang Ding, Changjian Li, Ruitong Huang

Figure 1 for CDT: Cascading Decision Trees for Explainable Reinforcement Learning
Figure 2 for CDT: Cascading Decision Trees for Explainable Reinforcement Learning
Figure 3 for CDT: Cascading Decision Trees for Explainable Reinforcement Learning
Figure 4 for CDT: Cascading Decision Trees for Explainable Reinforcement Learning

  Access Paper or Ask Questions

RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library


Sep 18, 2020
Zihan Ding, Tianyang Yu, Yanhua Huang, Hongming Zhang, Luo Mai, Hao Dong

Figure 1 for RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library
Figure 2 for RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library
Figure 3 for RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library
Figure 4 for RLzoo: A Comprehensive and Adaptive Reinforcement Learning Library
* Paper under submission at Journal of Machine Learning Research-Open Source Software 
  Access Paper or Ask Questions

Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics


Aug 15, 2020
Eugene Valassakis, Zihan Ding, Edward Johns

Figure 1 for Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics
Figure 2 for Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics
Figure 3 for Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics
Figure 4 for Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamics
* To be published at IROS 2020. 8 pages, 6 figures. For supplementary material and code, please visit : https://www.robot-learning.uk/crossing-the-gap 
  Access Paper or Ask Questions

Sim-to-Real Transfer for Optical Tactile Sensing


Mar 31, 2020
Zihan Ding, Nathan F. Lepora, Edward Johns

Figure 1 for Sim-to-Real Transfer for Optical Tactile Sensing
Figure 2 for Sim-to-Real Transfer for Optical Tactile Sensing
Figure 3 for Sim-to-Real Transfer for Optical Tactile Sensing
Figure 4 for Sim-to-Real Transfer for Optical Tactile Sensing
* Accepted for publication at ICRA 2020. Website: https://www.robot-learning.uk/sim-to-real-tactile-icra-2020 
  Access Paper or Ask Questions

Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence


May 30, 2019
Yuhang Song, Jianyi Wang, Thomas Lukasiewicz, Zhenghua Xu, Mai Xu, Zihan Ding, Lianlong Wu

Figure 1 for Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
Figure 2 for Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
Figure 3 for Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence
Figure 4 for Arena: A General Evaluation Platform and Building Toolkit for Multi-Agent Intelligence

  Access Paper or Ask Questions

TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation


Jan 28, 2019
Zihan Ding, Xiao-Yang Liu, Miao Yin, Wei Liu, Linghe Kong

Figure 1 for TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
Figure 2 for TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
Figure 3 for TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation
Figure 4 for TGAN: Deep Tensor Generative Adversarial Nets for Large Image Generation

  Access Paper or Ask Questions

Deep Reinforcement Learning for Intelligent Transportation Systems


Dec 03, 2018
Xiao-Yang Liu, Zihan Ding, Sem Borst, Anwar Walid

Figure 1 for Deep Reinforcement Learning for Intelligent Transportation Systems
Figure 2 for Deep Reinforcement Learning for Intelligent Transportation Systems
Figure 3 for Deep Reinforcement Learning for Intelligent Transportation Systems
Figure 4 for Deep Reinforcement Learning for Intelligent Transportation Systems

  Access Paper or Ask Questions