Matches in SemOpenAlex for { <https://semopenalex.org/work/W1538563646> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W1538563646 abstract "Advanced life support systems have many interacting processes and limited resources. Controlling and optimizing advanced life support systems presents unique challenges that are addressed in this paper. In particular, advanced life support systems are nonlinear coupled dynamical systems and it is difficult for humans to take all interactions into account to design an effective control strategy. We have developed a controller using reinforcement learning [1], that actively explores the space of possible control strategies, guided by rewards from a user specified long term objective function. We evaluated this controller using a discrete event simulation of an advanced life support system. This simulation, called BioSim, has multiple, interacting life support modules including crew, food production, air revitalization, water recovery, solid waste incineration and power. These are implemented in a consumer/producer relationship in which certain modules produce resources that are consumed by other modules. Stores hold resources between modules. Control of this simulation is via adjusting flows of resources between modules and into/out of stores. This paper describes the results of using reinforcement learning to control the flow of resources in BioSim. Our technique discovered unobvious strategies for maximizing mission length. By exploiting non-linearities in the simulation dynamics, the learned controller outperforms a handwritten controller." @default.
- W1538563646 created "2016-06-24" @default.
- W1538563646 creator A5020434909 @default.
- W1538563646 creator A5022956718 @default.
- W1538563646 creator A5058397549 @default.
- W1538563646 creator A5068285104 @default.
- W1538563646 date "2004-07-19" @default.
- W1538563646 modified "2023-10-18" @default.
- W1538563646 title "Using Reinforcement Learning to Control Life Support Systems" @default.
- W1538563646 cites W100525821 @default.
- W1538563646 cites W2097323078 @default.
- W1538563646 cites W2103626435 @default.
- W1538563646 cites W2107726111 @default.
- W1538563646 cites W2117341272 @default.
- W1538563646 cites W2121863487 @default.
- W1538563646 cites W2124175081 @default.
- W1538563646 cites W2125074935 @default.
- W1538563646 cites W2128281152 @default.
- W1538563646 cites W2145756561 @default.
- W1538563646 cites W2610686804 @default.
- W1538563646 cites W3011120880 @default.
- W1538563646 cites W3207021134 @default.
- W1538563646 cites W80219033 @default.
- W1538563646 doi "https://doi.org/10.4271/2004-01-2439" @default.
- W1538563646 hasPublicationYear "2004" @default.
- W1538563646 type Work @default.
- W1538563646 sameAs 1538563646 @default.
- W1538563646 citedByCount "9" @default.
- W1538563646 countsByYear W15385636462012 @default.
- W1538563646 countsByYear W15385636462013 @default.
- W1538563646 countsByYear W15385636462017 @default.
- W1538563646 countsByYear W15385636462019 @default.
- W1538563646 crossrefType "proceedings-article" @default.
- W1538563646 hasAuthorship W1538563646A5020434909 @default.
- W1538563646 hasAuthorship W1538563646A5022956718 @default.
- W1538563646 hasAuthorship W1538563646A5058397549 @default.
- W1538563646 hasAuthorship W1538563646A5068285104 @default.
- W1538563646 hasBestOaLocation W15385636462 @default.
- W1538563646 hasConcept C154945302 @default.
- W1538563646 hasConcept C2775924081 @default.
- W1538563646 hasConcept C41008148 @default.
- W1538563646 hasConcept C97541855 @default.
- W1538563646 hasConceptScore W1538563646C154945302 @default.
- W1538563646 hasConceptScore W1538563646C2775924081 @default.
- W1538563646 hasConceptScore W1538563646C41008148 @default.
- W1538563646 hasConceptScore W1538563646C97541855 @default.
- W1538563646 hasLocation W15385636461 @default.
- W1538563646 hasLocation W15385636462 @default.
- W1538563646 hasOpenAccess W1538563646 @default.
- W1538563646 hasPrimaryLocation W15385636461 @default.
- W1538563646 hasRelatedWork W1562959674 @default.
- W1538563646 hasRelatedWork W2923653485 @default.
- W1538563646 hasRelatedWork W2952472710 @default.
- W1538563646 hasRelatedWork W2957776456 @default.
- W1538563646 hasRelatedWork W3005560120 @default.
- W1538563646 hasRelatedWork W3037422413 @default.
- W1538563646 hasRelatedWork W4206669594 @default.
- W1538563646 hasRelatedWork W4255994452 @default.
- W1538563646 hasRelatedWork W4361026739 @default.
- W1538563646 hasRelatedWork W4372194388 @default.
- W1538563646 isParatext "false" @default.
- W1538563646 isRetracted "false" @default.
- W1538563646 magId "1538563646" @default.
- W1538563646 workType "article" @default.