Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890165259> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W2890165259 abstract "Optimal control is an important tool in many application areas, it is for example a central tool in robotics. Many widely used methods such as differential dynamic programming (DDP) are based on differentiating the dynamics of the controlled systems and the objective function. The assumption that one would have access to a differentiable model of the entire system does not hold for many systems of interest. For example, collisions break this assumption. In this case one has to resort to random search (Monte Carlo) algorithms. This thesis presents random search algorithms that fall into two categories. The first category is locally optimal sampling based trajectory optimization methods. The second one is real-time capable Monte Carlo tree search (MCTS) methods augmented with supervised machine learning. This thesis presents sampled differential dynamic programming (SaDDP), which is a random search trajectory optimization method, derived from the differential dynamic programming algorithm. SaDDP is derived by relating the quantities of the Taylor-expansion in DDP to the statistics of a multivariate normal distribution. This allows the statistics to be recomputed from sampled data instead of utilizing differentiation to obtain them. The thesis also presents ways to regularize the SaDDP algorithm efficiently. The real-time capable MCTS methods presented in this thesis enable the real-time control of complicated systems, such as physics-based 3D characters. The methods perform a receding horizon lookahead search and use the data produced by the lookahead search to teach machine learning models how to better search for the actions in the future. The demonstrated combination of receding horizon search and supervised learning is fast to converge and yields robust learning. The MCTS in this thesis combines information from multiple sources. This thesis presents how to combine the information from various sources in such a way that the search adapts to the information sources agreeing or disagreeing. In addition to new search algorithms, this thesis presents a combination of MCTS and a neural network generative model. This combination enables the neural network to learn that it can perform different actions in a single state.; Optimisaato on tarkea valine useilla sovellusalueilla, se on esimerkiksi keskeinen tyokalu robotiikassa. Monet laajasti kaytossa olevat menetelmat kuten differentiaalinen dynaaminen optimointi (DDP) perustuvat ohjatun jarjestelman dynamiikan ja kohdefunktion differentiointiin. Oletus jarjestelman mallin differentioituvuudesta ei pade monille jarjestelmille, joita halutaan saataa. Esimerkiksi tormaykset rikkovat kyseisen olettaman. Tassa tapauksessa on otettava kayttoon satunnaishaku- eli Monte Carlo algoritmit. Tassa vaitoskirjassa esitetyt satunnaishakualgoritmit jakautuvat kahteen kategoriaan. Toinen naista on lokaalisti optimaaliset satunnaishakuun perustuvat liikerataoptimointimenetelmat. Toinen kategorioista on reaaliaikaiseen ohjaukseen kykenevat Monte Carlo puuhakumenetelmat (MCTS),…" @default.
- W2890165259 created "2018-09-27" @default.
- W2890165259 creator A5004965619 @default.
- W2890165259 date "2018-01-01" @default.
- W2890165259 modified "2023-09-26" @default.
- W2890165259 title "Random Search Algorithms for Optimal Control" @default.
- W2890165259 hasPublicationYear "2018" @default.
- W2890165259 type Work @default.
- W2890165259 sameAs 2890165259 @default.
- W2890165259 citedByCount "0" @default.
- W2890165259 crossrefType "journal-article" @default.
- W2890165259 hasAuthorship W2890165259A5004965619 @default.
- W2890165259 hasConcept C105795698 @default.
- W2890165259 hasConcept C113174947 @default.
- W2890165259 hasConcept C11413529 @default.
- W2890165259 hasConcept C119857082 @default.
- W2890165259 hasConcept C125583679 @default.
- W2890165259 hasConcept C126255220 @default.
- W2890165259 hasConcept C126661757 @default.
- W2890165259 hasConcept C134306372 @default.
- W2890165259 hasConcept C154945302 @default.
- W2890165259 hasConcept C19499675 @default.
- W2890165259 hasConcept C33923547 @default.
- W2890165259 hasConcept C37404715 @default.
- W2890165259 hasConcept C41008148 @default.
- W2890165259 hasConcept C46149586 @default.
- W2890165259 hasConcept C92292787 @default.
- W2890165259 hasConceptScore W2890165259C105795698 @default.
- W2890165259 hasConceptScore W2890165259C113174947 @default.
- W2890165259 hasConceptScore W2890165259C11413529 @default.
- W2890165259 hasConceptScore W2890165259C119857082 @default.
- W2890165259 hasConceptScore W2890165259C125583679 @default.
- W2890165259 hasConceptScore W2890165259C126255220 @default.
- W2890165259 hasConceptScore W2890165259C126661757 @default.
- W2890165259 hasConceptScore W2890165259C134306372 @default.
- W2890165259 hasConceptScore W2890165259C154945302 @default.
- W2890165259 hasConceptScore W2890165259C19499675 @default.
- W2890165259 hasConceptScore W2890165259C33923547 @default.
- W2890165259 hasConceptScore W2890165259C37404715 @default.
- W2890165259 hasConceptScore W2890165259C41008148 @default.
- W2890165259 hasConceptScore W2890165259C46149586 @default.
- W2890165259 hasConceptScore W2890165259C92292787 @default.
- W2890165259 hasLocation W28901652591 @default.
- W2890165259 hasOpenAccess W2890165259 @default.
- W2890165259 hasPrimaryLocation W28901652591 @default.
- W2890165259 hasRelatedWork W1977702261 @default.
- W2890165259 hasRelatedWork W2009352103 @default.
- W2890165259 hasRelatedWork W2509546504 @default.
- W2890165259 hasRelatedWork W2543439725 @default.
- W2890165259 hasRelatedWork W2620687756 @default.
- W2890165259 hasRelatedWork W2738812390 @default.
- W2890165259 hasRelatedWork W2793020180 @default.
- W2890165259 hasRelatedWork W2803936899 @default.
- W2890165259 hasRelatedWork W2811063752 @default.
- W2890165259 hasRelatedWork W2886730169 @default.
- W2890165259 hasRelatedWork W2921756829 @default.
- W2890165259 hasRelatedWork W2962812027 @default.
- W2890165259 hasRelatedWork W2963557499 @default.
- W2890165259 hasRelatedWork W2969733916 @default.
- W2890165259 hasRelatedWork W3003471248 @default.
- W2890165259 hasRelatedWork W3036250521 @default.
- W2890165259 hasRelatedWork W3092482340 @default.
- W2890165259 hasRelatedWork W3175398266 @default.
- W2890165259 hasRelatedWork W3185513303 @default.
- W2890165259 hasRelatedWork W93759141 @default.
- W2890165259 isParatext "false" @default.
- W2890165259 isRetracted "false" @default.
- W2890165259 magId "2890165259" @default.
- W2890165259 workType "article" @default.