×
Aug 4, 2023 · We introduce a practical and theoretically grounded transition sampling approach to address action imbalance during offline RL training.
Feb 15, 2023 · We perform extensive experiments on two real-world tasks for diabetes and sepsis treatment optimization to compare performance of the proposed ...
We demonstrate that CQL, a SOTA offline RL method, can be applied in real-world treatment optimization applications to make recommendations that are more ...
Sep 7, 2024 · We provide theoretical analyses to show that our proposed approach would improve over CQL. We perform extensive experiments on two real-world ...
Notably, these works focused on making broad (largely drug class level) treatment recommendations independently of specific drug and dose considerations ...
Jul 16, 2023 · Video summary of our KDD'23 paper title “Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications” is live now!
Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications [2023] https://arxiv.org/abs/2302.07549; A dosing strategy model of deep ...
People also ask
Jul 26, 2023 · Deep reinforcement learning methods have great potential for identifying individualized medical treatments in many conditions.
Apr 25, 2024 · Deep Offline Reinforcement Learning for Real-world Treatment Optimization Applications. KDD 2023: 4673-4684. [i1]. view. electronic edition via ...