Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288360044> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4288360044 abstract "Deep reinforcement learning has proven to be successful for learning tasks in simulated environments, but applying same techniques for robots in real-world domain is more challenging, as they require hours of training. To address this, transfer learning can be used to train the policy first in a simulated environment and then transfer it to physical agent. As the simulation never matches reality perfectly, the physics, visuals and action spaces by necessity differ between these environments to some degree. In this work, we study how general video games can be directly used instead of fine-tuned simulations for the sim-to-real transfer. Especially, we study how the agent can learn the new action space autonomously, when the game actions do not match the robot actions. Our results show that the different action space can be learned by re-training only part of neural network and we obtain above 90% mean success rate in simulation and robot experiments." @default.
- W4288360044 created "2022-07-29" @default.
- W4288360044 creator A5037259225 @default.
- W4288360044 creator A5041496775 @default.
- W4288360044 creator A5048689678 @default.
- W4288360044 creator A5080940147 @default.
- W4288360044 date "2019-05-02" @default.
- W4288360044 modified "2023-09-24" @default.
- W4288360044 title "From Video Game to Real Robot: The Transfer between Action Spaces" @default.
- W4288360044 doi "https://doi.org/10.48550/arxiv.1905.00741" @default.
- W4288360044 hasPublicationYear "2019" @default.
- W4288360044 type Work @default.
- W4288360044 citedByCount "0" @default.
- W4288360044 crossrefType "posted-content" @default.
- W4288360044 hasAuthorship W4288360044A5037259225 @default.
- W4288360044 hasAuthorship W4288360044A5041496775 @default.
- W4288360044 hasAuthorship W4288360044A5048689678 @default.
- W4288360044 hasAuthorship W4288360044A5080940147 @default.
- W4288360044 hasBestOaLocation W42883600441 @default.
- W4288360044 hasConcept C107457646 @default.
- W4288360044 hasConcept C111919701 @default.
- W4288360044 hasConcept C121332964 @default.
- W4288360044 hasConcept C134306372 @default.
- W4288360044 hasConcept C150899416 @default.
- W4288360044 hasConcept C154945302 @default.
- W4288360044 hasConcept C173608175 @default.
- W4288360044 hasConcept C2776175482 @default.
- W4288360044 hasConcept C2778572836 @default.
- W4288360044 hasConcept C2780791683 @default.
- W4288360044 hasConcept C3018412434 @default.
- W4288360044 hasConcept C33923547 @default.
- W4288360044 hasConcept C36503486 @default.
- W4288360044 hasConcept C41008148 @default.
- W4288360044 hasConcept C44154836 @default.
- W4288360044 hasConcept C49774154 @default.
- W4288360044 hasConcept C50644808 @default.
- W4288360044 hasConcept C62520636 @default.
- W4288360044 hasConcept C90509273 @default.
- W4288360044 hasConcept C97541855 @default.
- W4288360044 hasConceptScore W4288360044C107457646 @default.
- W4288360044 hasConceptScore W4288360044C111919701 @default.
- W4288360044 hasConceptScore W4288360044C121332964 @default.
- W4288360044 hasConceptScore W4288360044C134306372 @default.
- W4288360044 hasConceptScore W4288360044C150899416 @default.
- W4288360044 hasConceptScore W4288360044C154945302 @default.
- W4288360044 hasConceptScore W4288360044C173608175 @default.
- W4288360044 hasConceptScore W4288360044C2776175482 @default.
- W4288360044 hasConceptScore W4288360044C2778572836 @default.
- W4288360044 hasConceptScore W4288360044C2780791683 @default.
- W4288360044 hasConceptScore W4288360044C3018412434 @default.
- W4288360044 hasConceptScore W4288360044C33923547 @default.
- W4288360044 hasConceptScore W4288360044C36503486 @default.
- W4288360044 hasConceptScore W4288360044C41008148 @default.
- W4288360044 hasConceptScore W4288360044C44154836 @default.
- W4288360044 hasConceptScore W4288360044C49774154 @default.
- W4288360044 hasConceptScore W4288360044C50644808 @default.
- W4288360044 hasConceptScore W4288360044C62520636 @default.
- W4288360044 hasConceptScore W4288360044C90509273 @default.
- W4288360044 hasConceptScore W4288360044C97541855 @default.
- W4288360044 hasLocation W42883600441 @default.
- W4288360044 hasOpenAccess W4288360044 @default.
- W4288360044 hasPrimaryLocation W42883600441 @default.
- W4288360044 hasRelatedWork W2468230436 @default.
- W4288360044 hasRelatedWork W2804727265 @default.
- W4288360044 hasRelatedWork W2805209921 @default.
- W4288360044 hasRelatedWork W2889970038 @default.
- W4288360044 hasRelatedWork W2937247296 @default.
- W4288360044 hasRelatedWork W2943584704 @default.
- W4288360044 hasRelatedWork W3003422588 @default.
- W4288360044 hasRelatedWork W3203489455 @default.
- W4288360044 hasRelatedWork W4221146601 @default.
- W4288360044 hasRelatedWork W4286908342 @default.
- W4288360044 isParatext "false" @default.
- W4288360044 isRetracted "false" @default.
- W4288360044 workType "article" @default.