Search Results for author: Flemming Kondrup

Found 2 papers, 1 papers with code

Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels

no code implementations16 Oct 2023 Thomas Jiralerspong, Flemming Kondrup, Doina Precup, Khimya Khetarpal

The ability to plan at many different levels of abstraction enables agents to envision the long-term repercussions of their decisions and thus enables sample-efficient learning.

Hierarchical Reinforcement Learning

Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning

1 code implementation5 Oct 2022 Flemming Kondrup, Thomas Jiralerspong, Elaine Lau, Nathan de Lara, Jacob Shkrob, My Duc Tran, Doina Precup, Sumana Basu

We design a clinically relevant intermediate reward that encourages continuous improvement of the patient vitals as well as addresses the challenge of sparse reward in RL.

Q-Learning reinforcement-learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.