Matches in SemOpenAlex for { <https://semopenalex.org/work/W2775408020> ?p ?o ?g. }
- W2775408020 abstract "Designing optimal controllers continues to be challenging as systems are becoming complex and are inherently nonlinear. The principal advantage of reinforcement learning (RL) is its ability to learn from the interaction with the environment and provide an optimal control strategy. In this paper, RL is explored in the context of control of the benchmark cart-pole dynamical system with no prior knowledge of the dynamics. RL algorithms such as temporal-difference, policy-gradient actorcritic, and value-function approximation are compared in this context with the standard linear quadratic regulator solution. Further, we propose a novel approach for integrating RL and swing-up controllers." @default.
- W2775408020 created "2017-12-22" @default.
- W2775408020 creator A5008718177 @default.
- W2775408020 creator A5037108669 @default.
- W2775408020 creator A5075746360 @default.
- W2775408020 creator A5087436359 @default.
- W2775408020 date "2017-09-01" @default.
- W2775408020 modified "2023-10-01" @default.
- W2775408020 title "Comparison of reinforcement learning algorithms applied to the cart-pole problem" @default.
- W2775408020 cites W166862392 @default.
- W2775408020 cites W2082374298 @default.
- W2775408020 cites W2084424121 @default.
- W2775408020 cites W2091565802 @default.
- W2775408020 cites W2102295697 @default.
- W2775408020 cites W2160989584 @default.
- W2775408020 cites W2539083524 @default.
- W2775408020 cites W3022436500 @default.
- W2775408020 cites W51114640 @default.
- W2775408020 doi "https://doi.org/10.1109/icacci.2017.8125811" @default.
- W2775408020 hasPublicationYear "2017" @default.
- W2775408020 type Work @default.
- W2775408020 sameAs 2775408020 @default.
- W2775408020 citedByCount "14" @default.
- W2775408020 countsByYear W27754080202018 @default.
- W2775408020 countsByYear W27754080202019 @default.
- W2775408020 countsByYear W27754080202020 @default.
- W2775408020 countsByYear W27754080202021 @default.
- W2775408020 countsByYear W27754080202022 @default.
- W2775408020 countsByYear W27754080202023 @default.
- W2775408020 crossrefType "proceedings-article" @default.
- W2775408020 hasAuthorship W2775408020A5008718177 @default.
- W2775408020 hasAuthorship W2775408020A5037108669 @default.
- W2775408020 hasAuthorship W2775408020A5075746360 @default.
- W2775408020 hasAuthorship W2775408020A5087436359 @default.
- W2775408020 hasBestOaLocation W27754080202 @default.
- W2775408020 hasConcept C11413529 @default.
- W2775408020 hasConcept C121332964 @default.
- W2775408020 hasConcept C126255220 @default.
- W2775408020 hasConcept C13280743 @default.
- W2775408020 hasConcept C14646407 @default.
- W2775408020 hasConcept C151730666 @default.
- W2775408020 hasConcept C154945302 @default.
- W2775408020 hasConcept C158622935 @default.
- W2775408020 hasConcept C185798385 @default.
- W2775408020 hasConcept C196340769 @default.
- W2775408020 hasConcept C205649164 @default.
- W2775408020 hasConcept C2775924081 @default.
- W2775408020 hasConcept C2779343474 @default.
- W2775408020 hasConcept C33923547 @default.
- W2775408020 hasConcept C41008148 @default.
- W2775408020 hasConcept C47446073 @default.
- W2775408020 hasConcept C50644808 @default.
- W2775408020 hasConcept C62520636 @default.
- W2775408020 hasConcept C79379906 @default.
- W2775408020 hasConcept C86803240 @default.
- W2775408020 hasConcept C91575142 @default.
- W2775408020 hasConcept C91873725 @default.
- W2775408020 hasConcept C97541855 @default.
- W2775408020 hasConcept C98779006 @default.
- W2775408020 hasConceptScore W2775408020C11413529 @default.
- W2775408020 hasConceptScore W2775408020C121332964 @default.
- W2775408020 hasConceptScore W2775408020C126255220 @default.
- W2775408020 hasConceptScore W2775408020C13280743 @default.
- W2775408020 hasConceptScore W2775408020C14646407 @default.
- W2775408020 hasConceptScore W2775408020C151730666 @default.
- W2775408020 hasConceptScore W2775408020C154945302 @default.
- W2775408020 hasConceptScore W2775408020C158622935 @default.
- W2775408020 hasConceptScore W2775408020C185798385 @default.
- W2775408020 hasConceptScore W2775408020C196340769 @default.
- W2775408020 hasConceptScore W2775408020C205649164 @default.
- W2775408020 hasConceptScore W2775408020C2775924081 @default.
- W2775408020 hasConceptScore W2775408020C2779343474 @default.
- W2775408020 hasConceptScore W2775408020C33923547 @default.
- W2775408020 hasConceptScore W2775408020C41008148 @default.
- W2775408020 hasConceptScore W2775408020C47446073 @default.
- W2775408020 hasConceptScore W2775408020C50644808 @default.
- W2775408020 hasConceptScore W2775408020C62520636 @default.
- W2775408020 hasConceptScore W2775408020C79379906 @default.
- W2775408020 hasConceptScore W2775408020C86803240 @default.
- W2775408020 hasConceptScore W2775408020C91575142 @default.
- W2775408020 hasConceptScore W2775408020C91873725 @default.
- W2775408020 hasConceptScore W2775408020C97541855 @default.
- W2775408020 hasConceptScore W2775408020C98779006 @default.
- W2775408020 hasLocation W27754080201 @default.
- W2775408020 hasLocation W27754080202 @default.
- W2775408020 hasLocation W27754080203 @default.
- W2775408020 hasOpenAccess W2775408020 @default.
- W2775408020 hasPrimaryLocation W27754080201 @default.
- W2775408020 hasRelatedWork W1624593201 @default.
- W2775408020 hasRelatedWork W1863485266 @default.
- W2775408020 hasRelatedWork W2069313024 @default.
- W2775408020 hasRelatedWork W2119031567 @default.
- W2775408020 hasRelatedWork W2149418961 @default.
- W2775408020 hasRelatedWork W2388285921 @default.
- W2775408020 hasRelatedWork W4239477580 @default.
- W2775408020 hasRelatedWork W4240668504 @default.
- W2775408020 hasRelatedWork W4289355352 @default.
- W2775408020 hasRelatedWork W4308702637 @default.
- W2775408020 isParatext "false" @default.
- W2775408020 isRetracted "false" @default.