Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290729704> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4290729704 endingPage "8161" @default.
- W4290729704 startingPage "8152" @default.
- W4290729704 abstract "Although reinforcement learning has been proved to be effective in many simulated platforms, it may still fail in environments due to the difference between simulation environment and real world environment, as well as being subjected to unexcepted attacks that objectively exist. Therefore, it calls for improving the robustness of the agent to increase its stability. To address the problem, an algorithm that uses the curiosity mechanism to improve the model exploration, referred to as instructive exploration adversarial robust reinforcement learning(Iearrl), is proposed, which enhances the adaption ability of agents through adversary learning, ensuring that the agent chooses a better action in practical environments with different settings from the training environment. At the same time, in order to increase the efficiency of exploration and reduce the cost, a model used to evaluate the competency of the agent is built for mentoring internal rewards determining whether further exploration is needed by analyzing the agent’s action in the current state space. The experiments in MuJoCo platforms verified the effectiveness of the proposed method." @default.
- W4290729704 created "2022-08-09" @default.
- W4290729704 creator A5048638476 @default.
- W4290729704 creator A5060107207 @default.
- W4290729704 creator A5074124642 @default.
- W4290729704 date "2022-11-01" @default.
- W4290729704 modified "2023-10-01" @default.
- W4290729704 title "Explore the weakness: Instructive exploration adversarial robust reinforcement learning" @default.
- W4290729704 cites W2077612644 @default.
- W4290729704 cites W2158782408 @default.
- W4290729704 cites W2766155583 @default.
- W4290729704 cites W2773691349 @default.
- W4290729704 cites W2963523627 @default.
- W4290729704 cites W2969123723 @default.
- W4290729704 cites W3034530016 @default.
- W4290729704 cites W3091895204 @default.
- W4290729704 cites W3092636900 @default.
- W4290729704 cites W3096831136 @default.
- W4290729704 cites W3119095582 @default.
- W4290729704 cites W3138349270 @default.
- W4290729704 cites W3200885897 @default.
- W4290729704 cites W3201016636 @default.
- W4290729704 cites W4214646922 @default.
- W4290729704 doi "https://doi.org/10.1016/j.jksuci.2022.08.001" @default.
- W4290729704 hasPublicationYear "2022" @default.
- W4290729704 type Work @default.
- W4290729704 citedByCount "0" @default.
- W4290729704 crossrefType "journal-article" @default.
- W4290729704 hasAuthorship W4290729704A5048638476 @default.
- W4290729704 hasAuthorship W4290729704A5060107207 @default.
- W4290729704 hasAuthorship W4290729704A5074124642 @default.
- W4290729704 hasBestOaLocation W42907297041 @default.
- W4290729704 hasConcept C104317684 @default.
- W4290729704 hasConcept C112930515 @default.
- W4290729704 hasConcept C112972136 @default.
- W4290729704 hasConcept C119857082 @default.
- W4290729704 hasConcept C121332964 @default.
- W4290729704 hasConcept C154945302 @default.
- W4290729704 hasConcept C15744967 @default.
- W4290729704 hasConcept C185592680 @default.
- W4290729704 hasConcept C2780791683 @default.
- W4290729704 hasConcept C33435437 @default.
- W4290729704 hasConcept C37736160 @default.
- W4290729704 hasConcept C38652104 @default.
- W4290729704 hasConcept C41008148 @default.
- W4290729704 hasConcept C41065033 @default.
- W4290729704 hasConcept C55493867 @default.
- W4290729704 hasConcept C62520636 @default.
- W4290729704 hasConcept C63479239 @default.
- W4290729704 hasConcept C71924100 @default.
- W4290729704 hasConcept C77805123 @default.
- W4290729704 hasConcept C97541855 @default.
- W4290729704 hasConceptScore W4290729704C104317684 @default.
- W4290729704 hasConceptScore W4290729704C112930515 @default.
- W4290729704 hasConceptScore W4290729704C112972136 @default.
- W4290729704 hasConceptScore W4290729704C119857082 @default.
- W4290729704 hasConceptScore W4290729704C121332964 @default.
- W4290729704 hasConceptScore W4290729704C154945302 @default.
- W4290729704 hasConceptScore W4290729704C15744967 @default.
- W4290729704 hasConceptScore W4290729704C185592680 @default.
- W4290729704 hasConceptScore W4290729704C2780791683 @default.
- W4290729704 hasConceptScore W4290729704C33435437 @default.
- W4290729704 hasConceptScore W4290729704C37736160 @default.
- W4290729704 hasConceptScore W4290729704C38652104 @default.
- W4290729704 hasConceptScore W4290729704C41008148 @default.
- W4290729704 hasConceptScore W4290729704C41065033 @default.
- W4290729704 hasConceptScore W4290729704C55493867 @default.
- W4290729704 hasConceptScore W4290729704C62520636 @default.
- W4290729704 hasConceptScore W4290729704C63479239 @default.
- W4290729704 hasConceptScore W4290729704C71924100 @default.
- W4290729704 hasConceptScore W4290729704C77805123 @default.
- W4290729704 hasConceptScore W4290729704C97541855 @default.
- W4290729704 hasFunder F4320321001 @default.
- W4290729704 hasFunder F4320322769 @default.
- W4290729704 hasFunder F4320327518 @default.
- W4290729704 hasFunder F4320333688 @default.
- W4290729704 hasIssue "10" @default.
- W4290729704 hasLocation W42907297041 @default.
- W4290729704 hasOpenAccess W4290729704 @default.
- W4290729704 hasPrimaryLocation W42907297041 @default.
- W4290729704 hasRelatedWork W2604394466 @default.
- W4290729704 hasRelatedWork W2773525213 @default.
- W4290729704 hasRelatedWork W2941205169 @default.
- W4290729704 hasRelatedWork W2952603690 @default.
- W4290729704 hasRelatedWork W2955689724 @default.
- W4290729704 hasRelatedWork W2964108292 @default.
- W4290729704 hasRelatedWork W2981396729 @default.
- W4290729704 hasRelatedWork W3158314496 @default.
- W4290729704 hasRelatedWork W3176644864 @default.
- W4290729704 hasRelatedWork W4290859889 @default.
- W4290729704 hasVolume "34" @default.
- W4290729704 isParatext "false" @default.
- W4290729704 isRetracted "false" @default.
- W4290729704 workType "article" @default.