Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951162110> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2951162110 abstract "Training deep neural network policies end-to-end for real-world applications so far requires big demonstration datasets in the real world or big sets consisting of a large variety of realistic and closely related 3D CAD models. These real or virtual data should, moreover, have very similar characteristics to the conditions expected at test time. These stringent requirements and the time consuming data collection processes that they entail, are currently the most important impediment that keeps deep reinforcement learning from being deployed in real-world applications. Therefore, in this work we advocate an alternative approach, where instead of avoiding any domain shift by carefully selecting the training data, the goal is to learn a policy that can cope with it. To this end, we propose the DoShiCo challenge: to train a model in very basic synthetic environments, far from realistic, in a way that it can be applied in more realistic environments as well as take the control decisions on real-world data. In particular, we focus on the task of collision avoidance for drones. We created a set of simulated environments that can be used as benchmark and implemented a baseline method, exploiting depth prediction as an auxiliary task to help overcome the domain shift. Even though the policy is trained in very basic environments, it can learn to fly without collisions in a very different realistic simulated environment. Of course several benchmarks for reinforcement learning already exist - but they never include a large domain shift. On the other hand, several benchmarks in computer vision focus on the domain shift, but they take the form of a static datasets instead of simulated environments. In this work we claim that it is crucial to take the two challenges together in one benchmark." @default.
- W2951162110 created "2019-06-27" @default.
- W2951162110 creator A5025186055 @default.
- W2951162110 creator A5074816094 @default.
- W2951162110 date "2017-10-26" @default.
- W2951162110 modified "2023-09-27" @default.
- W2951162110 title "DoShiCo Challenge: Domain Shift in Control Prediction" @default.
- W2951162110 hasPublicationYear "2017" @default.
- W2951162110 type Work @default.
- W2951162110 sameAs 2951162110 @default.
- W2951162110 citedByCount "0" @default.
- W2951162110 crossrefType "posted-content" @default.
- W2951162110 hasAuthorship W2951162110A5025186055 @default.
- W2951162110 hasAuthorship W2951162110A5074816094 @default.
- W2951162110 hasConcept C107457646 @default.
- W2951162110 hasConcept C108583219 @default.
- W2951162110 hasConcept C111368507 @default.
- W2951162110 hasConcept C119857082 @default.
- W2951162110 hasConcept C124101348 @default.
- W2951162110 hasConcept C12725497 @default.
- W2951162110 hasConcept C127313418 @default.
- W2951162110 hasConcept C127413603 @default.
- W2951162110 hasConcept C13280743 @default.
- W2951162110 hasConcept C134306372 @default.
- W2951162110 hasConcept C136197465 @default.
- W2951162110 hasConcept C154945302 @default.
- W2951162110 hasConcept C177264268 @default.
- W2951162110 hasConcept C185798385 @default.
- W2951162110 hasConcept C199360897 @default.
- W2951162110 hasConcept C201995342 @default.
- W2951162110 hasConcept C205649164 @default.
- W2951162110 hasConcept C2775924081 @default.
- W2951162110 hasConcept C2780451532 @default.
- W2951162110 hasConcept C33923547 @default.
- W2951162110 hasConcept C36503486 @default.
- W2951162110 hasConcept C41008148 @default.
- W2951162110 hasConcept C50644808 @default.
- W2951162110 hasConcept C54355233 @default.
- W2951162110 hasConcept C59519942 @default.
- W2951162110 hasConcept C75684735 @default.
- W2951162110 hasConcept C86803240 @default.
- W2951162110 hasConcept C97541855 @default.
- W2951162110 hasConceptScore W2951162110C107457646 @default.
- W2951162110 hasConceptScore W2951162110C108583219 @default.
- W2951162110 hasConceptScore W2951162110C111368507 @default.
- W2951162110 hasConceptScore W2951162110C119857082 @default.
- W2951162110 hasConceptScore W2951162110C124101348 @default.
- W2951162110 hasConceptScore W2951162110C12725497 @default.
- W2951162110 hasConceptScore W2951162110C127313418 @default.
- W2951162110 hasConceptScore W2951162110C127413603 @default.
- W2951162110 hasConceptScore W2951162110C13280743 @default.
- W2951162110 hasConceptScore W2951162110C134306372 @default.
- W2951162110 hasConceptScore W2951162110C136197465 @default.
- W2951162110 hasConceptScore W2951162110C154945302 @default.
- W2951162110 hasConceptScore W2951162110C177264268 @default.
- W2951162110 hasConceptScore W2951162110C185798385 @default.
- W2951162110 hasConceptScore W2951162110C199360897 @default.
- W2951162110 hasConceptScore W2951162110C201995342 @default.
- W2951162110 hasConceptScore W2951162110C205649164 @default.
- W2951162110 hasConceptScore W2951162110C2775924081 @default.
- W2951162110 hasConceptScore W2951162110C2780451532 @default.
- W2951162110 hasConceptScore W2951162110C33923547 @default.
- W2951162110 hasConceptScore W2951162110C36503486 @default.
- W2951162110 hasConceptScore W2951162110C41008148 @default.
- W2951162110 hasConceptScore W2951162110C50644808 @default.
- W2951162110 hasConceptScore W2951162110C54355233 @default.
- W2951162110 hasConceptScore W2951162110C59519942 @default.
- W2951162110 hasConceptScore W2951162110C75684735 @default.
- W2951162110 hasConceptScore W2951162110C86803240 @default.
- W2951162110 hasConceptScore W2951162110C97541855 @default.
- W2951162110 hasLocation W29511621101 @default.
- W2951162110 hasOpenAccess W2951162110 @default.
- W2951162110 hasPrimaryLocation W29511621101 @default.
- W2951162110 hasRelatedWork W1536894604 @default.
- W2951162110 hasRelatedWork W1564998426 @default.
- W2951162110 hasRelatedWork W1618113455 @default.
- W2951162110 hasRelatedWork W2070775927 @default.
- W2951162110 hasRelatedWork W2296212956 @default.
- W2951162110 hasRelatedWork W2473111106 @default.
- W2951162110 hasRelatedWork W2510962294 @default.
- W2951162110 hasRelatedWork W2560186857 @default.
- W2951162110 hasRelatedWork W2607497913 @default.
- W2951162110 hasRelatedWork W2738381667 @default.
- W2951162110 hasRelatedWork W2766864503 @default.
- W2951162110 hasRelatedWork W2767124462 @default.
- W2951162110 hasRelatedWork W2792604159 @default.
- W2951162110 hasRelatedWork W2808184406 @default.
- W2951162110 hasRelatedWork W2888831604 @default.
- W2951162110 hasRelatedWork W2892141954 @default.
- W2951162110 hasRelatedWork W2958095304 @default.
- W2951162110 hasRelatedWork W3008400579 @default.
- W2951162110 hasRelatedWork W3176904586 @default.
- W2951162110 hasRelatedWork W3927766 @default.
- W2951162110 isParatext "false" @default.
- W2951162110 isRetracted "false" @default.
- W2951162110 magId "2951162110" @default.
- W2951162110 workType "article" @default.