Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208375534> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3208375534 abstract "One's ability to learn a generative model of the world without supervision depends on the extent to which one can construct abstract knowledge representations that generalize across experiences. To this end, capturing an accurate statistical structure from observational data provides useful inductive biases that can be transferred to novel environments. Here, we tackle the problem of learning to control dynamical systems by applying Bayesian nonparametric methods, which is applied to solve visual servoing tasks. This is accomplished by first learning a state space representation, then inferring environmental dynamics and improving the policies through imagined future trajectories. Bayesian nonparametric models provide automatic model adaptation, which not only combats underfitting and overfitting, but also allows the model's unbounded dimension to be both flexible and computationally tractable. By employing Gaussian processes to discover latent world dynamics, we mitigate common data efficiency issues observed in reinforcement learning and avoid introducing explicit model bias by describing the system's dynamics. Our algorithm jointly learns a world model and policy by optimizing a variational lower bound of a log-likelihood with respect to the expected free energy minimization objective function. Finally, we compare the performance of our model with the state-of-the-art alternatives for continuous control tasks in simulated environments." @default.
- W3208375534 created "2021-11-08" @default.
- W3208375534 creator A5009537716 @default.
- W3208375534 creator A5045533727 @default.
- W3208375534 creator A5059737776 @default.
- W3208375534 creator A5071926428 @default.
- W3208375534 creator A5071941660 @default.
- W3208375534 creator A5091902222 @default.
- W3208375534 date "2021-10-27" @default.
- W3208375534 modified "2023-09-28" @default.
- W3208375534 title "Dream to Explore: Adaptive Simulations for Autonomous Systems." @default.
- W3208375534 cites W1522301498 @default.
- W3208375534 cites W2951004968 @default.
- W3208375534 cites W3093963693 @default.
- W3208375534 cites W3102488324 @default.
- W3208375534 hasPublicationYear "2021" @default.
- W3208375534 type Work @default.
- W3208375534 sameAs 3208375534 @default.
- W3208375534 citedByCount "0" @default.
- W3208375534 crossrefType "posted-content" @default.
- W3208375534 hasAuthorship W3208375534A5009537716 @default.
- W3208375534 hasAuthorship W3208375534A5045533727 @default.
- W3208375534 hasAuthorship W3208375534A5059737776 @default.
- W3208375534 hasAuthorship W3208375534A5071926428 @default.
- W3208375534 hasAuthorship W3208375534A5071941660 @default.
- W3208375534 hasAuthorship W3208375534A5091902222 @default.
- W3208375534 hasConcept C107673813 @default.
- W3208375534 hasConcept C119857082 @default.
- W3208375534 hasConcept C154945302 @default.
- W3208375534 hasConcept C167966045 @default.
- W3208375534 hasConcept C17744445 @default.
- W3208375534 hasConcept C199539241 @default.
- W3208375534 hasConcept C202444582 @default.
- W3208375534 hasConcept C22019652 @default.
- W3208375534 hasConcept C2776359362 @default.
- W3208375534 hasConcept C33676613 @default.
- W3208375534 hasConcept C33923547 @default.
- W3208375534 hasConcept C39890363 @default.
- W3208375534 hasConcept C41008148 @default.
- W3208375534 hasConcept C50644808 @default.
- W3208375534 hasConcept C94625758 @default.
- W3208375534 hasConcept C97541855 @default.
- W3208375534 hasConceptScore W3208375534C107673813 @default.
- W3208375534 hasConceptScore W3208375534C119857082 @default.
- W3208375534 hasConceptScore W3208375534C154945302 @default.
- W3208375534 hasConceptScore W3208375534C167966045 @default.
- W3208375534 hasConceptScore W3208375534C17744445 @default.
- W3208375534 hasConceptScore W3208375534C199539241 @default.
- W3208375534 hasConceptScore W3208375534C202444582 @default.
- W3208375534 hasConceptScore W3208375534C22019652 @default.
- W3208375534 hasConceptScore W3208375534C2776359362 @default.
- W3208375534 hasConceptScore W3208375534C33676613 @default.
- W3208375534 hasConceptScore W3208375534C33923547 @default.
- W3208375534 hasConceptScore W3208375534C39890363 @default.
- W3208375534 hasConceptScore W3208375534C41008148 @default.
- W3208375534 hasConceptScore W3208375534C50644808 @default.
- W3208375534 hasConceptScore W3208375534C94625758 @default.
- W3208375534 hasConceptScore W3208375534C97541855 @default.
- W3208375534 hasOpenAccess W3208375534 @default.
- W3208375534 hasRelatedWork W2121615264 @default.
- W3208375534 hasRelatedWork W2186581219 @default.
- W3208375534 hasRelatedWork W2245825236 @default.
- W3208375534 hasRelatedWork W2404067440 @default.
- W3208375534 hasRelatedWork W2765363933 @default.
- W3208375534 hasRelatedWork W2809088500 @default.
- W3208375534 hasRelatedWork W2959258437 @default.
- W3208375534 hasRelatedWork W2963745201 @default.
- W3208375534 hasRelatedWork W2970515169 @default.
- W3208375534 hasRelatedWork W2986406093 @default.
- W3208375534 hasRelatedWork W2989966838 @default.
- W3208375534 hasRelatedWork W3006592782 @default.
- W3208375534 hasRelatedWork W3012496101 @default.
- W3208375534 hasRelatedWork W3015838160 @default.
- W3208375534 hasRelatedWork W3016965513 @default.
- W3208375534 hasRelatedWork W3018228603 @default.
- W3208375534 hasRelatedWork W3088002337 @default.
- W3208375534 hasRelatedWork W3124636427 @default.
- W3208375534 hasRelatedWork W3197221587 @default.
- W3208375534 hasRelatedWork W2611766042 @default.
- W3208375534 isParatext "false" @default.
- W3208375534 isRetracted "false" @default.
- W3208375534 magId "3208375534" @default.
- W3208375534 workType "article" @default.