Wenhao Li

Wenhao Li

Auto-generated profile, based on publicly available information

Wenhao Li

School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society 518172 Shenzhen China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 August 2022 in Autonomous Agents and Multi-Agent Systems
Verified
Journal Article
Closed access
PDF file
JSJunjie Sheng
Junjie Sheng
XWXiangfeng Wang
Xiangfeng Wang
BJBo Jin
Bo Jin
Junchi YanJunchi Yan
Junchi Yan
WLWenhao Li
Wenhao Li
HZHongyuan Zha
Hongyuan Zha

4 August 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
WLWenhao Li
Wenhao Li
XWXiangfeng Wang
Xiangfeng Wang
BJBo Jin
Bo Jin
DLDijun Luo
Dijun Luo
HZHongyuan Zha
Hongyuan Zha
In recent years, reinforcement learning has achieved excellent results in low-dimensional static action spaces such as games and simple robotics. However, the action space is usually composite, composed of multiple sub-action with different functions, and time-varying for practical tasks. The existing sub-actions might be temporarily invalid due to the external environment, while unseen sub-actions can be added to the current system. To solve the robustness and transferability problems in time-varying composite action spaces, we propose a structured cooperative reinforcement learning algorithm based on the centralized critic and decentralized actor framework, called SCORE. We model the single-agent problem with composite action space as a fully cooperative partially observable stochastic game and further employ a graph attention network to capture the dependencies between heterogeneous sub-actions. To promote tighter cooperation between the decomposed heterogeneous agents, SCORE introduces a hierarchical variational autoencoder, which maps the heterogeneous sub-action space into a common latent action space. We also incorporate an implicit credit assignment structure into the SCORE to overcome the multi-agent credit assignment problem in the fully cooperative partially observable stochastic game. Performance experiments on the proof-of-concept task and precision agriculture task show that SCORE has significant advantages in robustness and transferability for time-varying composite action space.

30 December 2019 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
XWXiangfeng Wang
Xiangfeng Wang
Junchi YanJunchi Yan
Junchi Yan
BJBo Jin
Bo Jin
WLWenhao Li
Wenhao Li
The nonconvex optimization problems have recently attracted significant attention. However, both efficient algorithm and solid theory are still very limited. The difficulty is even pronounced for structured large-scale problems in many real-world applications. This article proposes an application-driven algorithmic framework for structured nonconvex optimization problems with distributed and parallel techniques, which jointly handles the high dimensionality of model parameters and distributed training data. The theoretical convergence of our algorithm is established under moderate assumptions. We apply the proposed method to popular multitask applications, including a multitask reinforcement learning problem. The promising performance demonstrates our framework is effective and efficient.

22 September 2023 in Frontiers of Information Technology & Electronic Engineering
Verified
Journal Article
Closed access
PDF file
CSChuyun Shen
Chuyun Shen
WLWenhao Li
Wenhao Li
QXQisen Xu
Qisen Xu
BHBin Hu
Bin Hu
BJBo Jin
Bo Jin
XWXiangfeng Wang
Xiangfeng Wang
Interactive medical image segmentation based on human-in-the-loop machine learning is a novel paradigm that draws on human expert knowledge to assist medic

6 September 2024 in Neural Networks
Verified
Journal Article
Closed access
CSChuyun Shen
Chuyun Shen
WLWenhao Li
Wenhao Li
HCHaoqing Chen
Haoqing Chen
XWXiaoling Wang
Xiaoling Wang
FZFengping Zhu
Fengping Zhu
BJBo Jin
Bo Jin

14 August 2021
Verified
Conference Paper
Open access
YHYun Hua
Yun Hua
XWXiangfeng Wang
Xiangfeng Wang
BJBo Jin
Bo Jin
WLWenhao Li
Wenhao Li
Junchi YanJunchi Yan
Junchi Yan
HZHongyuan Zha
Hongyuan Zha
In spite of the success of existing meta reinforcement learning methods, they still have difficulty in learning a meta policy effectively for RL problems with sparse reward. In this respect, we develop a novel meta reinforcement learning framework called Hyper-Meta RL(HMRL), for sparse reward RL problems. It is consisted with three modules including the cross-environment meta state embedding module which constructs a common meta state space to adapt to different environments; the meta state based environment-specific meta reward shaping which effectively extends the original sparse reward trajectory by cross-environmental knowledge complementarity and as a consequence the meta policy achieves better generalization and efficiency with the shaped meta reward. Experiments with sparse-reward environments show the superiority of HMRL on both transferability and policy learning efficiency.