Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288045472> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4288045472 endingPage "200105" @default.
- W4288045472 startingPage "200105" @default.
- W4288045472 abstract "In toy environments like video games, a reinforcement learning agent is deployed and operates within the same state space in which it was trained. However, in robotics applications such as industrial systems or autonomous vehicles, this cannot be guaranteed. A robot can be pushed out of its training space by some unforeseen perturbation, which may cause it to go into an unknown state from which it has not been trained to move towards its goal. While most prior work in the area of RL safety focuses on ensuring safety in the training phase, this paper focuses on ensuring the safe deployment of a robot that has already been trained to operate within a safe space. This work defines a condition on the state and action spaces, that if satisfied, guarantees the robot’s recovery to safety independently. We also propose a strategy and design that facilitate this recovery within a finite number of steps after perturbation. This is implemented and tested against a standard RL model, and the results indicate a significant improvement in performance." @default.
- W4288045472 created "2022-07-27" @default.
- W4288045472 creator A5022062449 @default.
- W4288045472 creator A5055571512 @default.
- W4288045472 date "2022-11-01" @default.
- W4288045472 modified "2023-10-18" @default.
- W4288045472 title "Safe deployment of a reinforcement learning robot using self stabilization" @default.
- W4288045472 cites W2074500080 @default.
- W4288045472 cites W2095425626 @default.
- W4288045472 cites W2111132249 @default.
- W4288045472 cites W2774977638 @default.
- W4288045472 cites W2963293747 @default.
- W4288045472 cites W3009331570 @default.
- W4288045472 cites W3100944043 @default.
- W4288045472 doi "https://doi.org/10.1016/j.iswa.2022.200105" @default.
- W4288045472 hasPublicationYear "2022" @default.
- W4288045472 type Work @default.
- W4288045472 citedByCount "0" @default.
- W4288045472 crossrefType "journal-article" @default.
- W4288045472 hasAuthorship W4288045472A5022062449 @default.
- W4288045472 hasAuthorship W4288045472A5055571512 @default.
- W4288045472 hasBestOaLocation W42880454721 @default.
- W4288045472 hasConcept C105339364 @default.
- W4288045472 hasConcept C105795698 @default.
- W4288045472 hasConcept C107457646 @default.
- W4288045472 hasConcept C115903868 @default.
- W4288045472 hasConcept C154945302 @default.
- W4288045472 hasConcept C33923547 @default.
- W4288045472 hasConcept C34413123 @default.
- W4288045472 hasConcept C41008148 @default.
- W4288045472 hasConcept C44154836 @default.
- W4288045472 hasConcept C72434380 @default.
- W4288045472 hasConcept C90509273 @default.
- W4288045472 hasConcept C97541855 @default.
- W4288045472 hasConceptScore W4288045472C105339364 @default.
- W4288045472 hasConceptScore W4288045472C105795698 @default.
- W4288045472 hasConceptScore W4288045472C107457646 @default.
- W4288045472 hasConceptScore W4288045472C115903868 @default.
- W4288045472 hasConceptScore W4288045472C154945302 @default.
- W4288045472 hasConceptScore W4288045472C33923547 @default.
- W4288045472 hasConceptScore W4288045472C34413123 @default.
- W4288045472 hasConceptScore W4288045472C41008148 @default.
- W4288045472 hasConceptScore W4288045472C44154836 @default.
- W4288045472 hasConceptScore W4288045472C72434380 @default.
- W4288045472 hasConceptScore W4288045472C90509273 @default.
- W4288045472 hasConceptScore W4288045472C97541855 @default.
- W4288045472 hasLocation W42880454721 @default.
- W4288045472 hasLocation W42880454722 @default.
- W4288045472 hasLocation W42880454723 @default.
- W4288045472 hasOpenAccess W4288045472 @default.
- W4288045472 hasPrimaryLocation W42880454721 @default.
- W4288045472 hasRelatedWork W2937603438 @default.
- W4288045472 hasRelatedWork W2959276766 @default.
- W4288045472 hasRelatedWork W3074294383 @default.
- W4288045472 hasRelatedWork W3158304547 @default.
- W4288045472 hasRelatedWork W405964254 @default.
- W4288045472 hasRelatedWork W4206669594 @default.
- W4288045472 hasRelatedWork W4221165949 @default.
- W4288045472 hasRelatedWork W4233452137 @default.
- W4288045472 hasRelatedWork W4254857216 @default.
- W4288045472 hasRelatedWork W4292103105 @default.
- W4288045472 hasVolume "16" @default.
- W4288045472 isParatext "false" @default.
- W4288045472 isRetracted "false" @default.
- W4288045472 workType "article" @default.