Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283796247> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4283796247 endingPage "105106" @default.
- W4283796247 startingPage "105106" @default.
- W4283796247 abstract "We present a case study of model-free reinforcement learning (RL) framework to solve stochastic optimal control for a predefined parameter uncertainty distribution and partially observable system. We focus on robust optimal well control problem which is a subject of intensive research activities in the field of subsurface reservoir management. For this problem, the system is partially observed since the data is only available at well locations. Furthermore, the model parameters are highly uncertain due to sparsity of available field data. In principle, RL algorithms are capable of learning optimal action policies -- a map from states to actions -- to maximize a numerical reward signal. In deep RL, this mapping from state to action is parameterized using a deep neural network. In the RL formulation of the robust optimal well control problem, the states are represented by saturation and pressure values at well locations while the actions represent the valve openings controlling the flow through wells. The numerical reward refers to the total sweep efficiency and the uncertain model parameter is the subsurface permeability field. The model parameter uncertainties are handled by introducing a domain randomisation scheme that exploits cluster analysis on its uncertainty distribution. We present numerical results using two state-of-the-art RL algorithms, proximal policy optimization (PPO) and advantage actor-critic (A2C), on two subsurface flow test cases representing two distinct uncertainty distributions of permeability field. The results were benchmarked against optimisation results obtained using differential evolution algorithm. Furthermore, we demonstrate the robustness of the proposed use of RL by evaluating the learned control policy on unseen samples drawn from the parameter uncertainty distribution that were not used during the training process." @default.
- W4283796247 created "2022-07-05" @default.
- W4283796247 creator A5007464582 @default.
- W4283796247 creator A5073082543 @default.
- W4283796247 date "2022-09-01" @default.
- W4283796247 modified "2023-09-30" @default.
- W4283796247 title "Stochastic optimal well control in subsurface reservoirs using reinforcement learning" @default.
- W4283796247 cites W1595159159 @default.
- W4283796247 cites W2049670620 @default.
- W4283796247 cites W2066406884 @default.
- W4283796247 cites W2157164625 @default.
- W4283796247 cites W2384046304 @default.
- W4283796247 cites W2592001929 @default.
- W4283796247 cites W2772589676 @default.
- W4283796247 cites W2888317899 @default.
- W4283796247 cites W3099401519 @default.
- W4283796247 cites W3103145119 @default.
- W4283796247 doi "https://doi.org/10.1016/j.engappai.2022.105106" @default.
- W4283796247 hasPublicationYear "2022" @default.
- W4283796247 type Work @default.
- W4283796247 citedByCount "6" @default.
- W4283796247 countsByYear W42837962472022 @default.
- W4283796247 countsByYear W42837962472023 @default.
- W4283796247 crossrefType "journal-article" @default.
- W4283796247 hasAuthorship W4283796247A5007464582 @default.
- W4283796247 hasAuthorship W4283796247A5073082543 @default.
- W4283796247 hasBestOaLocation W42837962472 @default.
- W4283796247 hasConcept C104317684 @default.
- W4283796247 hasConcept C11413529 @default.
- W4283796247 hasConcept C126255220 @default.
- W4283796247 hasConcept C154945302 @default.
- W4283796247 hasConcept C165464430 @default.
- W4283796247 hasConcept C185592680 @default.
- W4283796247 hasConcept C33923547 @default.
- W4283796247 hasConcept C41008148 @default.
- W4283796247 hasConcept C50644808 @default.
- W4283796247 hasConcept C55493867 @default.
- W4283796247 hasConcept C63479239 @default.
- W4283796247 hasConcept C91575142 @default.
- W4283796247 hasConcept C97541855 @default.
- W4283796247 hasConceptScore W4283796247C104317684 @default.
- W4283796247 hasConceptScore W4283796247C11413529 @default.
- W4283796247 hasConceptScore W4283796247C126255220 @default.
- W4283796247 hasConceptScore W4283796247C154945302 @default.
- W4283796247 hasConceptScore W4283796247C165464430 @default.
- W4283796247 hasConceptScore W4283796247C185592680 @default.
- W4283796247 hasConceptScore W4283796247C33923547 @default.
- W4283796247 hasConceptScore W4283796247C41008148 @default.
- W4283796247 hasConceptScore W4283796247C50644808 @default.
- W4283796247 hasConceptScore W4283796247C55493867 @default.
- W4283796247 hasConceptScore W4283796247C63479239 @default.
- W4283796247 hasConceptScore W4283796247C91575142 @default.
- W4283796247 hasConceptScore W4283796247C97541855 @default.
- W4283796247 hasFunder F4320311518 @default.
- W4283796247 hasFunder F4320334627 @default.
- W4283796247 hasLocation W42837962471 @default.
- W4283796247 hasLocation W42837962472 @default.
- W4283796247 hasLocation W42837962473 @default.
- W4283796247 hasOpenAccess W4283796247 @default.
- W4283796247 hasPrimaryLocation W42837962471 @default.
- W4283796247 hasRelatedWork W2357085366 @default.
- W4283796247 hasRelatedWork W2370949144 @default.
- W4283796247 hasRelatedWork W2896049690 @default.
- W4283796247 hasRelatedWork W2906331936 @default.
- W4283796247 hasRelatedWork W2950685899 @default.
- W4283796247 hasRelatedWork W2959276766 @default.
- W4283796247 hasRelatedWork W2963257680 @default.
- W4283796247 hasRelatedWork W3021426118 @default.
- W4283796247 hasRelatedWork W3074294383 @default.
- W4283796247 hasRelatedWork W4206669594 @default.
- W4283796247 hasVolume "114" @default.
- W4283796247 isParatext "false" @default.
- W4283796247 isRetracted "false" @default.
- W4283796247 workType "article" @default.