Constrained control of large graph-based MDPs under measurement uncertainty
RN Haksar, M Schwager - IEEE Transactions on Automatic …, 2023 - ieeexplore.ieee.org
We consider controlling a graph-based Markov decision process (GMDP) with a control
capacity constraint given only uncertain measurements of the underlying state. We also …
capacity constraint given only uncertain measurements of the underlying state. We also …
UAV-based Firefighting by Multi-agent Reinforcement Learning
RS Tanha, M Hooshmand… - 2023 13th International …, 2023 - ieeexplore.ieee.org
Wildfire in the forest leads to a huge amount of financial and human losses. That is it causes
damage to the forest and the life of firefighters. To reduce the amount of such damage …
damage to the forest and the life of firefighters. To reduce the amount of such damage …
Learning large graph-based MDPs with historical data
RN Haksar, M Schwager - IEEE Transactions on Control of …, 2021 - ieeexplore.ieee.org
Weconsider learning the dynamics and measurement model parameters of a graph-based
Markov decision process (GMDP) given a history of measurements. Graph-based models …
Markov decision process (GMDP) given a history of measurements. Graph-based models …
[图书][B] Control, Filtering, Learning, and Multi-Robot Algorithms for Large Graph-Based Markov Decision Processes
RN Haksar - 2020 - search.proquest.com
This thesis derives a series of algorithms to enable the use of a class of structured models,
known as graph-based Markov decision processes (GMDPs), for applications involving a …
known as graph-based Markov decision processes (GMDPs), for applications involving a …