Zheng.H
Zheng.H
Home
Posts
Projects
Talks
Publications
Contact
CV
Light
Dark
Automatic
Reinforcement Learning
Policy Optimization in Bayesian Network Hybrid Models of Biomanufacturing Processes
Biopharmaceutical manufacturing is a rapidly growing industry with impact in virtually all branches of medicine. Biomanufacturing …
Hua Zheng
,
Wei Xie
,
Ilya O Ryzhov
,
Dongming Xie
PDF
Cite
Code
DOI
Variance Reduction based Experience Replay for Policy Optimization
Can a reinforcement learning (RL) agent remember and learn from the past, just like a human? Short answer: “yes but only after selecting relevant and valuable experiences from the memory.” I am glad to announce my new paper and its open-source project, both built on my research about “variance reduction based experience replay” (VRER). Long story short, VRER is a generic experience replay method with provable sample efficiency.
VRER makes the reinforcementlearning agent remember by selectively replaying past experiences
. This selective mechanism can adaptively filter out samples that are outdated, irrelevant and unstable. Our empirical study shows that VRER substantially improves the state-of-the-art policy optimization algorithms, such as trust region policy optimization and proximal policy optimization, in both convergence speed and robustness.
Hua Zheng
,
Wei Xie
,
M Ben Feng
PDF
Cite
Code
Some Gaps Between Reinforcement Learning Practice and Theory
Some concerns on reinforcement learning algorithms.
Hua Zheng
May 8, 2022
5 min read
Blog
32nd Annual POMS-Conference (Talk 2)
Knowledge Graph Hybrid Model-based Bayesian Reinforcement Learning for Cell Therapy Manufacturing Process Control
Apr 25, 2022 2:00 PM — 1:00 PM
Virtual
Hua Zheng
,
Wei Xie
,
Keqi Wang
,
Zheng Li
Slides
Follow
Github
Linkedin
Opportunities of Hybrid Model-based Reinforcement Learning for Cell Therapy Manufacturing Process Development and Control
Hua Zheng
,
Wei Xie
,
Keqi Wang
,
Zheng Li
PDF
Cite
Personalized Multimorbidity Management for Patients with Type 2 Diabetes Using Reinforcement Learning of Electronic Health Records
Background
: Comorbid chronic conditions are common among people with type 2 diabetes. We developed an artificial intelligence …
Hua Zheng
,
Ilya O. Ryzhov
,
Wei Xie
,
Judy Zhong
PDF
Cite
Code
Video
DOI
EHR-RL
Personalized multimorbidity management for patients with type 2 diabetes using reinforcement learning of electronic health records.
PDF
Code
Video
Reinforcement Learning Assisted Oxygen Therapy for COVID-19 Patients Under Intensive Care
Background:
Patients with severe Coronavirus disease 19 (COVID-19) typically require supplemental oxygen as an essential treatment. We …
Hua Zheng
,
Jiahao Zhu
,
Wei Xie
,
Judy Zhong
PDF
Cite
DOI
Winter Simulation Conference 2020
Green Simulation Assisted Reinforcement Learning with Model Risk for Biomanufacturing Learning and Control.
Dec 15, 2020 10:30 AM — 11:00 AM
Virtual
Hua Zheng
,
Wei Xie
,
M. Ben Feng
PDF
Code
Slides
Follow
Github
Linkedin
Green Simulation Assisted Reinforcement Learning with Model Risk for Biomanufacturing Learning and Control
Biopharmaceutical manufacturing faces critical challenges, including complexity, high variability, lengthy lead time, and limited …
Hua Zheng
,
Wei Xie
,
M. Ben Feng
PDF
Cite
Code
Cite
×