Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892858663> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2892858663 abstract "Reinforcement learning methods have recently achieved impressive results on a wide range of control problems. However, especially with complex inputs, they still require an extensive amount of training data in order to converge to a meaningful solution. This limits their applicability to complex input spaces such as video signals, and makes them impractical for use in complex real world problems, including many of those for video based control. Supervised learning, on the contrary, is capable of learning on a relatively limited number of samples, but relies on arbitrary hand-labelling of data rather than task-derived reward functions, and hence do not yield independent control policies. In this article we propose a novel, model-free approach, which uses a combination of reinforcement and supervised learning for autonomous control and paves the way towards policy based control in real world environments. We use SpeedDreams/TORCS video game to demonstrate that our approach requires much less samples (hundreds of thousands against millions or tens of millions) comparing to the state-of-the-art reinforcement learning techniques on similar data, and at the same time overcomes both supervised and reinforcement learning approaches in terms of quality. Additionally, we demonstrate applicability of the method to MuJoCo control problems." @default.
- W2892858663 created "2018-10-05" @default.
- W2892858663 creator A5079755748 @default.
- W2892858663 creator A5087140377 @default.
- W2892858663 date "2018-07-01" @default.
- W2892858663 modified "2023-09-25" @default.
- W2892858663 title "Continuous Control With a Combination of Supervised and Reinforcement Learning" @default.
- W2892858663 cites W124618424 @default.
- W2892858663 cites W1623881903 @default.
- W2892858663 cites W1665214252 @default.
- W2892858663 cites W1757796397 @default.
- W2892858663 cites W1980287119 @default.
- W2892858663 cites W2097117768 @default.
- W2892858663 cites W2163605009 @default.
- W2892858663 cites W2165150801 @default.
- W2892858663 cites W2173248099 @default.
- W2892858663 cites W2271840356 @default.
- W2892858663 cites W2274287116 @default.
- W2892858663 cites W2291973609 @default.
- W2892858663 cites W2470394683 @default.
- W2892858663 cites W2566057350 @default.
- W2892858663 cites W2581117323 @default.
- W2892858663 cites W2593897087 @default.
- W2892858663 cites W2726187156 @default.
- W2892858663 cites W2727840223 @default.
- W2892858663 cites W2741122588 @default.
- W2892858663 cites W2964043796 @default.
- W2892858663 cites W2964121744 @default.
- W2892858663 cites W2965916140 @default.
- W2892858663 doi "https://doi.org/10.1109/ijcnn.2018.8489702" @default.
- W2892858663 hasPublicationYear "2018" @default.
- W2892858663 type Work @default.
- W2892858663 sameAs 2892858663 @default.
- W2892858663 citedByCount "0" @default.
- W2892858663 crossrefType "proceedings-article" @default.
- W2892858663 hasAuthorship W2892858663A5079755748 @default.
- W2892858663 hasAuthorship W2892858663A5087140377 @default.
- W2892858663 hasBestOaLocation W28928586632 @default.
- W2892858663 hasConcept C111472728 @default.
- W2892858663 hasConcept C119857082 @default.
- W2892858663 hasConcept C127413603 @default.
- W2892858663 hasConcept C136389625 @default.
- W2892858663 hasConcept C138885662 @default.
- W2892858663 hasConcept C146978453 @default.
- W2892858663 hasConcept C154945302 @default.
- W2892858663 hasConcept C196340769 @default.
- W2892858663 hasConcept C201995342 @default.
- W2892858663 hasConcept C204323151 @default.
- W2892858663 hasConcept C2775924081 @default.
- W2892858663 hasConcept C2779530757 @default.
- W2892858663 hasConcept C2780451532 @default.
- W2892858663 hasConcept C41008148 @default.
- W2892858663 hasConcept C50644808 @default.
- W2892858663 hasConcept C97541855 @default.
- W2892858663 hasConceptScore W2892858663C111472728 @default.
- W2892858663 hasConceptScore W2892858663C119857082 @default.
- W2892858663 hasConceptScore W2892858663C127413603 @default.
- W2892858663 hasConceptScore W2892858663C136389625 @default.
- W2892858663 hasConceptScore W2892858663C138885662 @default.
- W2892858663 hasConceptScore W2892858663C146978453 @default.
- W2892858663 hasConceptScore W2892858663C154945302 @default.
- W2892858663 hasConceptScore W2892858663C196340769 @default.
- W2892858663 hasConceptScore W2892858663C201995342 @default.
- W2892858663 hasConceptScore W2892858663C204323151 @default.
- W2892858663 hasConceptScore W2892858663C2775924081 @default.
- W2892858663 hasConceptScore W2892858663C2779530757 @default.
- W2892858663 hasConceptScore W2892858663C2780451532 @default.
- W2892858663 hasConceptScore W2892858663C41008148 @default.
- W2892858663 hasConceptScore W2892858663C50644808 @default.
- W2892858663 hasConceptScore W2892858663C97541855 @default.
- W2892858663 hasLocation W28928586631 @default.
- W2892858663 hasLocation W28928586632 @default.
- W2892858663 hasOpenAccess W2892858663 @default.
- W2892858663 hasPrimaryLocation W28928586631 @default.
- W2892858663 hasRelatedWork W2142789491 @default.
- W2892858663 hasRelatedWork W2293550301 @default.
- W2892858663 hasRelatedWork W3022038857 @default.
- W2892858663 hasRelatedWork W3035324854 @default.
- W2892858663 hasRelatedWork W3162567751 @default.
- W2892858663 hasRelatedWork W3209810506 @default.
- W2892858663 hasRelatedWork W3210156800 @default.
- W2892858663 hasRelatedWork W4226172683 @default.
- W2892858663 hasRelatedWork W4231499115 @default.
- W2892858663 hasRelatedWork W4319083788 @default.
- W2892858663 isParatext "false" @default.
- W2892858663 isRetracted "false" @default.
- W2892858663 magId "2892858663" @default.
- W2892858663 workType "article" @default.