Matches in SemOpenAlex for { <https://semopenalex.org/work/W3099409848> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3099409848 abstract "Steel production is a complex problem, and little has been done to improve it with the usage of Reinforcement Learning techniques. Most studies focus on decomposing it into sub-problems, instead of tacking it as a whole. Research has shown promising results in the area of safe policy improvement on toy problems. These algorithms are not only computationally tractable but also do not compromise the agent's safety concerns during learning. This thesis investigates how they perform on the real-world problem of improving steel production logistics. We take a simulation of a steel plant that uses hand-crafted heuristics for scheduling tasks and model it as a Markov Decision Process. We experiment with safe policy improvement algorithms by using different baseline policies. Given problem suffers from the known ''Curse of dimensionality''. Hence, the algorithms are adjusted to cope with the fast-expanding complexity. The methods prove to learn with fewer amount of samples than exploration methods. The results are especially promising with a highly stochastic baseline policy, as then the agent has a better understanding of the large environment. The next focus is on the factored representation, which has the advantage of better utilizing the problem. However, in our setting, the algorithms become too computationally expensive." @default.
- W3099409848 created "2020-11-23" @default.
- W3099409848 creator A5018346394 @default.
- W3099409848 date "2020-01-01" @default.
- W3099409848 modified "2023-09-27" @default.
- W3099409848 title "Safe Optimization of Steel Manufacturing with Reinforcement Learning" @default.
- W3099409848 hasPublicationYear "2020" @default.
- W3099409848 type Work @default.
- W3099409848 sameAs 3099409848 @default.
- W3099409848 citedByCount "0" @default.
- W3099409848 crossrefType "journal-article" @default.
- W3099409848 hasAuthorship W3099409848A5018346394 @default.
- W3099409848 hasConcept C105795698 @default.
- W3099409848 hasConcept C106189395 @default.
- W3099409848 hasConcept C111030470 @default.
- W3099409848 hasConcept C111368507 @default.
- W3099409848 hasConcept C111919701 @default.
- W3099409848 hasConcept C119857082 @default.
- W3099409848 hasConcept C126255220 @default.
- W3099409848 hasConcept C12725497 @default.
- W3099409848 hasConcept C127313418 @default.
- W3099409848 hasConcept C127413603 @default.
- W3099409848 hasConcept C127705205 @default.
- W3099409848 hasConcept C154945302 @default.
- W3099409848 hasConcept C159886148 @default.
- W3099409848 hasConcept C206729178 @default.
- W3099409848 hasConcept C2779181239 @default.
- W3099409848 hasConcept C33923547 @default.
- W3099409848 hasConcept C41008148 @default.
- W3099409848 hasConcept C78519656 @default.
- W3099409848 hasConcept C97541855 @default.
- W3099409848 hasConceptScore W3099409848C105795698 @default.
- W3099409848 hasConceptScore W3099409848C106189395 @default.
- W3099409848 hasConceptScore W3099409848C111030470 @default.
- W3099409848 hasConceptScore W3099409848C111368507 @default.
- W3099409848 hasConceptScore W3099409848C111919701 @default.
- W3099409848 hasConceptScore W3099409848C119857082 @default.
- W3099409848 hasConceptScore W3099409848C126255220 @default.
- W3099409848 hasConceptScore W3099409848C12725497 @default.
- W3099409848 hasConceptScore W3099409848C127313418 @default.
- W3099409848 hasConceptScore W3099409848C127413603 @default.
- W3099409848 hasConceptScore W3099409848C127705205 @default.
- W3099409848 hasConceptScore W3099409848C154945302 @default.
- W3099409848 hasConceptScore W3099409848C159886148 @default.
- W3099409848 hasConceptScore W3099409848C206729178 @default.
- W3099409848 hasConceptScore W3099409848C2779181239 @default.
- W3099409848 hasConceptScore W3099409848C33923547 @default.
- W3099409848 hasConceptScore W3099409848C41008148 @default.
- W3099409848 hasConceptScore W3099409848C78519656 @default.
- W3099409848 hasConceptScore W3099409848C97541855 @default.
- W3099409848 hasLocation W30994098481 @default.
- W3099409848 hasOpenAccess W3099409848 @default.
- W3099409848 hasPrimaryLocation W30994098481 @default.
- W3099409848 hasRelatedWork W144003339 @default.
- W3099409848 hasRelatedWork W148042338 @default.
- W3099409848 hasRelatedWork W1570407429 @default.
- W3099409848 hasRelatedWork W2603217374 @default.
- W3099409848 hasRelatedWork W2789965303 @default.
- W3099409848 hasRelatedWork W2807421416 @default.
- W3099409848 hasRelatedWork W3011578045 @default.
- W3099409848 hasRelatedWork W3037462640 @default.
- W3099409848 hasRelatedWork W3082908097 @default.
- W3099409848 hasRelatedWork W3116111955 @default.
- W3099409848 hasRelatedWork W3122770905 @default.
- W3099409848 hasRelatedWork W312649961 @default.
- W3099409848 hasRelatedWork W3132741523 @default.
- W3099409848 hasRelatedWork W3153014104 @default.
- W3099409848 hasRelatedWork W3198152645 @default.
- W3099409848 hasRelatedWork W3200219384 @default.
- W3099409848 hasRelatedWork W3203079382 @default.
- W3099409848 hasRelatedWork W3206820021 @default.
- W3099409848 hasRelatedWork W3210375194 @default.
- W3099409848 hasRelatedWork W2575464687 @default.
- W3099409848 isParatext "false" @default.
- W3099409848 isRetracted "false" @default.
- W3099409848 magId "3099409848" @default.
- W3099409848 workType "article" @default.