1 code implementation • 18 Sep 2020 • Zihan Ding, Tianyang Yu, Yanhua Huang, Hongming Zhang, Guo Li, Quancheng Guo, Luo Mai, Hao Dong
RLzoo provides developers with (i) high-level yet flexible APIs for prototyping DRL agents, and further customising the agents for best performance, (ii) a model zoo where users can import a wide range of DRL agents and easily compare their performance, and (iii) an algorithm that can automatically construct DRL agents with custom components (which are critical to improve agent's performance in custom applications).
2 code implementations • 17 May 2019 • Yuhang Song, Andrzej Wojcicki, Thomas Lukasiewicz, Jianyi Wang, Abi Aryan, Zhenghua Xu, Mai Xu, Zihan Ding, Lianlong Wu
That is, there is not yet a general evaluation platform for research on multi-agent intelligence.
1 code implementation • CVPR 2023 • Luting Wang, Yi Liu, Penghui Du, Zihan Ding, Yue Liao, Qiaosong Qi, Biaolong Chen, Si Liu
When extracting object knowledge from PVLMs, the former adaptively transforms object proposals and adopts object-aware mask attention to obtain precise and complete knowledge of objects.
Ranked #13 on Open Vocabulary Object Detection on MSCOCO
2 code implementations • 18 Jul 2022 • Zihan Ding, DiJia Su, Qinghua Liu, Chi Jin
This paper proposes new, end-to-end deep reinforcement learning algorithms for learning two-player zero-sum Markov games.
1 code implementation • 15 Nov 2020 • Zihan Ding, Pablo Hernandez-Leal, Gavin Weiguang Ding, Changjian Li, Ruitong Huang
As a second contribution our study reveals limitations of explaining black-box policies via imitation learning with tree-based explainable models, due to its inherent instability.
1 code implementation • CVPR 2022 • Zihan Ding, Tianrui Hui, Junshi Huang, Xiaoming Wei, Jizhong Han, Si Liu
Referring video object segmentation aims to predict foreground labels for objects referred by natural language expressions in videos.
Ranked #5 on Referring Video Object Segmentation on MeViS
1 code implementation • 29 Sep 2023 • Zihan Ding, Chi Jin
We propose to apply the consistency model as an efficient yet expressive policy representation, namely consistency policy, with an actor-critic style algorithm for three typical RL settings: offline, offline-to-online and online.
1 code implementation • 28 Jan 2019 • Zihan Ding, Xiao-Yang Liu, Miao Yin, Linghe Kong
Secondly, we propose TGAN that integrates deep convolutional generative adversarial networks and tensor super-resolution in a cascading manner, to generate high-quality images from random distributions.
1 code implementation • 11 Aug 2022 • Zihan Ding, Zi-han Ding, Tianrui Hui, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Si Liu
To alleviate these drawbacks, we propose a one-stage end-to-end Pixel-Phrase Matching Network (PPMN), which directly matches each phrase to its corresponding pixels instead of region proposals and outputs panoptic segmentation by simple combination.
1 code implementation • 19 Apr 2021 • Jie Ren, Yewen Li, Zihan Ding, Wei Pan, Hao Dong
However, grasping distinguishable skills for some tasks with non-unique optima can be essential for further improving its learning efficiency and performance, which may lead to a multimodal policy represented as a mixture-of-experts (MOE).
1 code implementation • 3 Jun 2022 • Zhiyuan Yao, Zihan Ding
A fully distributed MARL algorithm is proposed to approximate the Nash equilibrium of the game.
no code implementations • 3 Dec 2018 • Xiao-Yang Liu, Zihan Ding, Sem Borst, Anwar Walid
Intelligent Transportation Systems (ITSs) are envisioned to play a critical role in improving traffic flow and reducing congestion, which is a pervasive issue impacting urban areas around the globe.
no code implementations • 15 Aug 2020 • Eugene Valassakis, Zihan Ding, Edward Johns
Zero-shot sim-to-real transfer of tasks with complex dynamics is a highly challenging and unsolved problem.
no code implementations • 22 Feb 2021 • Ya-Yen Tsai, Hui Xu, Zihan Ding, Chong Zhang, Edward Johns, Bidan Huang
One of the main challenges of transferring the policy learned in a simulated environment to real world, is the discrepancy between the dynamics of the two environments.
Robotics
no code implementations • CVPR 2021 • Tianrui Hui, Shaofei Huang, Si Liu, Zihan Ding, Guanbin Li, Wenguan Wang, Jizhong Han, Fei Wang
Though 3D convolutions are amenable to recognizing which actor is performing the queried actions, it also inevitably introduces misaligned spatial information from adjacent frames, which confuses features of the target frame and yields inaccurate segmentation.
Ranked #8 on Referring Expression Segmentation on J-HMDB
no code implementations • 29 Oct 2021 • Zhiyuan Yao, Zihan Ding, Thomas Heide Clausen
Network load balancers are central components in data centers, that distributes workloads across multiple servers and thereby contribute to offering scalable services.
no code implementations • 27 Jan 2022 • Zhiyuan Yao, Zihan Ding, Thomas Clausen
This paper presents the network load balancing problem, a challenging real-world task for multi-agent reinforcement learning (MARL) methods.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 10 Apr 2023 • Zihan Ding, Yuanpei Chen, Allen Z. Ren, Shixiang Shane Gu, Qianxu Wang, Hao Dong, Chi Jin
Generating human-like behavior on robots is a great challenge especially in dexterous manipulation tasks with robotic hands.
no code implementations • 18 Sep 2023 • Zihan Ding, Xiaoxi Wei, Yidan Xu
Human consciousness has been a long-lasting mystery for centuries, while machine intelligence and consciousness is an arduous pursuit.
no code implementations • 2 Nov 2023 • Tianrui Hui, Zihan Ding, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Jiao Dai, Jizhong Han, Si Liu
Panoptic narrative grounding (PNG) aims to segment things and stuff objects in an image described by noun phrases of a narrative caption.
no code implementations • 5 Feb 2024 • Zihan Ding, Amy Zhang, Yuandong Tian, Qinqing Zheng
We introduce Diffusion World Model (DWM), a conditional diffusion model capable of predicting multistep future states and rewards concurrently.
no code implementations • 25 Mar 2024 • Si Liu, Zihan Ding, Jiahui Fu, Hongyu Li, Siheng Chen, Shifeng Zhang, Xu Zhou
The point cluster inherently preserves object information while packing messages, with weak relevance to the collaboration range, and supports explicit structure modeling.