Matches in SemOpenAlex for { <https://semopenalex.org/work/W2785369214> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2785369214 abstract "We use model-free reinforcement learning, extensive simulation, and transfer learning to develop a continuous control algorithm that has good zero-shot performance in a real physical environment. We train a simulated agent to act optimally across a set of similar environments, each with dynamics drawn from a prior distribution. We propose that the agent is able to adjust its actions almost immediately, based on small set of observations. This robust and adaptive behavior is enabled by using a policy gradient algorithm with an Long Short Term Memory (LSTM) function approximation. Finally, we train an agent to navigate a two-dimensional environment with uncertain dynamics and noisy observations. We demonstrate that this agent has good zero-shot performance in a real physical environment. Our preliminary results indicate that the agent is able to infer the environmental dynamics after only a few timesteps, and adjust its actions accordingly." @default.
- W2785369214 created "2018-02-23" @default.
- W2785369214 creator A5008053913 @default.
- W2785369214 creator A5067562300 @default.
- W2785369214 date "2018-02-13" @default.
- W2785369214 modified "2023-09-27" @default.
- W2785369214 title "Learning Robust and Adaptive Real-World Continuous Control Using Simulation and Transfer Learning" @default.
- W2785369214 cites W1588998206 @default.
- W2785369214 cites W1737105075 @default.
- W2785369214 cites W2059706201 @default.
- W2785369214 cites W2117629901 @default.
- W2785369214 cites W2121863487 @default.
- W2785369214 cites W2141604475 @default.
- W2785369214 cites W2173248099 @default.
- W2785369214 cites W2205975260 @default.
- W2785369214 cites W2302255633 @default.
- W2785369214 cites W2342662072 @default.
- W2785369214 cites W2530944449 @default.
- W2785369214 cites W2541674938 @default.
- W2785369214 cites W2556958149 @default.
- W2785369214 cites W2560647685 @default.
- W2785369214 cites W2736601468 @default.
- W2785369214 cites W2749928749 @default.
- W2785369214 cites W2949608212 @default.
- W2785369214 cites W2951084826 @default.
- W2785369214 cites W2964161785 @default.
- W2785369214 hasPublicationYear "2018" @default.
- W2785369214 type Work @default.
- W2785369214 sameAs 2785369214 @default.
- W2785369214 citedByCount "0" @default.
- W2785369214 crossrefType "posted-content" @default.
- W2785369214 hasAuthorship W2785369214A5008053913 @default.
- W2785369214 hasAuthorship W2785369214A5067562300 @default.
- W2785369214 hasConcept C121332964 @default.
- W2785369214 hasConcept C125014702 @default.
- W2785369214 hasConcept C138885662 @default.
- W2785369214 hasConcept C145912823 @default.
- W2785369214 hasConcept C150899416 @default.
- W2785369214 hasConcept C154945302 @default.
- W2785369214 hasConcept C177264268 @default.
- W2785369214 hasConcept C199360897 @default.
- W2785369214 hasConcept C24890656 @default.
- W2785369214 hasConcept C2775924081 @default.
- W2785369214 hasConcept C2780813799 @default.
- W2785369214 hasConcept C41008148 @default.
- W2785369214 hasConcept C41895202 @default.
- W2785369214 hasConcept C97541855 @default.
- W2785369214 hasConceptScore W2785369214C121332964 @default.
- W2785369214 hasConceptScore W2785369214C125014702 @default.
- W2785369214 hasConceptScore W2785369214C138885662 @default.
- W2785369214 hasConceptScore W2785369214C145912823 @default.
- W2785369214 hasConceptScore W2785369214C150899416 @default.
- W2785369214 hasConceptScore W2785369214C154945302 @default.
- W2785369214 hasConceptScore W2785369214C177264268 @default.
- W2785369214 hasConceptScore W2785369214C199360897 @default.
- W2785369214 hasConceptScore W2785369214C24890656 @default.
- W2785369214 hasConceptScore W2785369214C2775924081 @default.
- W2785369214 hasConceptScore W2785369214C2780813799 @default.
- W2785369214 hasConceptScore W2785369214C41008148 @default.
- W2785369214 hasConceptScore W2785369214C41895202 @default.
- W2785369214 hasConceptScore W2785369214C97541855 @default.
- W2785369214 hasLocation W27853692141 @default.
- W2785369214 hasOpenAccess W2785369214 @default.
- W2785369214 hasPrimaryLocation W27853692141 @default.
- W2785369214 hasRelatedWork W2099320314 @default.
- W2785369214 hasRelatedWork W2111770102 @default.
- W2785369214 hasRelatedWork W2121103318 @default.
- W2785369214 hasRelatedWork W2743381431 @default.
- W2785369214 hasRelatedWork W2898290017 @default.
- W2785369214 hasRelatedWork W2905438253 @default.
- W2785369214 hasRelatedWork W2923252998 @default.
- W2785369214 hasRelatedWork W2950004691 @default.
- W2785369214 hasRelatedWork W2952902960 @default.
- W2785369214 hasRelatedWork W2953084784 @default.
- W2785369214 hasRelatedWork W2996793228 @default.
- W2785369214 hasRelatedWork W3012330110 @default.
- W2785369214 hasRelatedWork W3015442441 @default.
- W2785369214 hasRelatedWork W3093118788 @default.
- W2785369214 hasRelatedWork W3104268834 @default.
- W2785369214 hasRelatedWork W3105320065 @default.
- W2785369214 hasRelatedWork W3131063630 @default.
- W2785369214 hasRelatedWork W3139185958 @default.
- W2785369214 hasRelatedWork W3181350748 @default.
- W2785369214 hasRelatedWork W3211148793 @default.
- W2785369214 isParatext "false" @default.
- W2785369214 isRetracted "false" @default.
- W2785369214 magId "2785369214" @default.
- W2785369214 workType "article" @default.