Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space

Wang, Zeyu; Zhao, Huiying; Ren, Peng; Zhou, Yue; Sheng, Ming

doi:10.1007/978-3-031-20627-6_11

Cited by 7 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BooT [74] s-a-r-R data augmentation, decoder D4RL teacher-forcing strategy [142] state-marginal CDT [143] s-a matching decoder Gym, MuJoCo BDT [143] s-a decoder Gym, MuJoCo h-a (SLT) Scene-Rep [144] s (MST) SAC encoder-decoder SMARTS [145] SPLT [146] s-a encoder-decoder CARLA [147] Trans-REIN [148] s REINFORCE encoder-decoder TSP instance STT [149] s -encoder Gym, Mujoco, CausalWorld [150] Catformer [151] -R2D2 [152] decoder Quake III Arena Engine GTrXL [153] s decoder DMLab-30, Memory Maze Gambling, Connect Four, ESPER [154] s-a encoder 2048 [155] Meta-RL AdA [174] o-a-r auto-curriculum learning encoder XLand 2.0 decoder Transformer structure (shown in Fig. 11) to enhance the parallelization for proximal policy optimization (PPO).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Transformer in Reinforcement Learning for Decision-Making: A Survey

Yuan¹,

Chen²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Reinforcement learning (RL) has become a dominant decision-making paradigm and has achieved notable success in many real-world applications, such as autonomous driving, robotic manipulation, robotic navigation and gaming AI. However, the powerful abilities of the RL variants were developed with advanced machine learning techniques. For example, deep neural networks play a crucial role in unlocking RL’s potential in large-scale decision-making tasks. Inspired by present day major successes of Transformer in natural language processing and computer vision, numerous bottlenecks have been overcome by combining Transformer with RL for decision-making. This paper presents a multiangle systematic survey of various Transformerbased RL (TransRL) models applied in decision-making tasks, including basic models, advanced algorithms, representative implementation instances, applications, and known challenges. Our work aims to provide insights into problems that inherently arise with the current RL approaches, and examines how we can address them with better TransRL models. To our knowledge, we are the first to present a comprehensive review of the recent Transformers research developments in RL for decisionmaking. We hope this survey provides a comprehensive review of TransRL models and also inspires the RL community in its pursuit of future directions. Finally, to keep track of the rapid TransRL developments in the decision-making domains, we summarize the latest relevant papers and their open-source implementations at https://github.com/williamyuanv0/Transformerin-Reinforcement-Learning-for-Decision-Making-A-Survey.</p>

show abstract

Section: Methodsmentioning

confidence: 99%

“…More details will be introduced in Sec.IV-A. Wang et al [74] also provided a perspective by viewing the offline RL as a generic sequence generation problem, adopting Transformer architecture to model distributions over trajectories.…”

Section: A Transformer-based Offline Rlmentioning

confidence: 99%

Transformer in Reinforcement Learning for Decision-Making: A Survey

Yuan¹,

Chen²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Currently, researchers use DRL models, such as Proximal Policy Optimization (PPO), to find the optimal contracts. Inspired by diffusion Q-learning [15], we integrate the diffusion process in conventional DRL to improve its flexibility and exploration ability. To help readers understand the fourstep workflow mentioned in Section III-D, we elaborate our diffusion-empowered contract generation step-by-step.…”

Section: Diffusion-empowered Contract Generationmentioning

confidence: 99%

“…• Step 2: Explore the policy in latent space. We use a conditional diffusion model to exploit the latent space of contract generation [15]. Specifically, we need to learn the policy π(c 0 |s) for generating the optimal contract c 0 under the state s ∈ {S}.…”

Section: Diffusion-empowered Contract Generationmentioning

confidence: 99%

“…Then, we build a DRL model to gradually refine π(c 0 |s) until it can find the c 0 which leads to the highest Q. Specifically, we employ a double-Q DRL architecture [15], consisting of two Q-networks and two target networks. Two Q-networks are updated in an alternating fashion, i.e., each one learns from the other's experience to avoid overestimation.…”

Section: Diffusion-empowered Contract Generationmentioning

confidence: 99%

See 1 more Smart Citation

A Study Of Civil Engineering Education At Singapore Nanyang Technology University And At The University Of Florida

Liu¹,

Najafi²

2002 Annual Conference Proceedings

View full text Add to dashboard Cite

offer civil engineering courses to undergraduate and graduate students. This paper discusses and compares Civil Engineering curriculum in both Universities. The Civil Engineering courses at the University of Florida are divided into two phases of general education and upper division/civil engineering core education. At Nanyang Technology University, the Civil Engineering offers courses of a prescribed core of essential subjects and both institutions offer excellent program of study. The Civil Engineering program at Nanyang Technology University offers courses closely related to industry and government needs. Similarly, at the University of Florida, Civil Engineering program also offers excellent education program in line with government and industries needs. At both institutions, efforts should be focused on revising curriculum that is more responsible to existing and future rapid technological changes.

show abstract

Glucocorticoid therapy for sepsis in the AI era: a survey on current and future approaches

Liang,

Pan,

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space

Cited by 7 publications

References 11 publications

Transformer in Reinforcement Learning for Decision-Making: A Survey

Transformer in Reinforcement Learning for Decision-Making: A Survey

A Study Of Civil Engineering Education At Singapore Nanyang Technology University And At The University Of Florida

Glucocorticoid therapy for sepsis in the AI era: a survey on current and future approaches

Contact Info

Product

Resources

About