Matches in SemOpenAlex for { <https://semopenalex.org/work/W2012805624> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2012805624 abstract "Recently, reinforcement learning attracts attention as the learning technique that is often used on actual robot. As one of problems of reinforcement learning, it is difficult for reinforcement learning to cope with changing purpose, because reinforcement learning depend on reward. Until now, we suggested that we learned to use information does not depend on reward for solving the problem. This information is environmental transition. We defined this information as “Reward-Independent Knowledge (RIK)”. A robot gets RIK and predicts route from initial state to purpose state by using RIK. Reinforcement learning can cope with changing purpose by using RIK. However, it is difficult for RIK to cope with dynamic environment, because RIK is one to one correspondence between state-action pair and next state. Therefore, we suggest that RIK has multiple next state and probability of each possible next state. In this paper, we perform an experiment by simulation. We show that suggested knowledge copes with changing purpose and dynamic environment. In this experiment, we adopt a maze problem which a goal change and changing structure of maze. By this, we will show that suggested knowledge can cope with changing purpose and dynamic environment." @default.
- W2012805624 created "2016-06-24" @default.
- W2012805624 creator A5002014695 @default.
- W2012805624 creator A5005896891 @default.
- W2012805624 creator A5067555059 @default.
- W2012805624 date "2011-11-01" @default.
- W2012805624 modified "2023-10-16" @default.
- W2012805624 title "Suggestion of probabilistic reward-independent knowledge for dynamic environment in reinforcement learning" @default.
- W2012805624 cites W1507591516 @default.
- W2012805624 cites W2042357378 @default.
- W2012805624 cites W2114235770 @default.
- W2012805624 cites W2121517924 @default.
- W2012805624 cites W2144752499 @default.
- W2012805624 cites W2145983895 @default.
- W2012805624 cites W2152166054 @default.
- W2012805624 cites W2167647761 @default.
- W2012805624 cites W2518102996 @default.
- W2012805624 cites W2911283634 @default.
- W2012805624 cites W2914656440 @default.
- W2012805624 doi "https://doi.org/10.1109/mhs.2011.6102175" @default.
- W2012805624 hasPublicationYear "2011" @default.
- W2012805624 type Work @default.
- W2012805624 sameAs 2012805624 @default.
- W2012805624 citedByCount "0" @default.
- W2012805624 crossrefType "proceedings-article" @default.
- W2012805624 hasAuthorship W2012805624A5002014695 @default.
- W2012805624 hasAuthorship W2012805624A5005896891 @default.
- W2012805624 hasAuthorship W2012805624A5067555059 @default.
- W2012805624 hasConcept C11413529 @default.
- W2012805624 hasConcept C119857082 @default.
- W2012805624 hasConcept C121332964 @default.
- W2012805624 hasConcept C154945302 @default.
- W2012805624 hasConcept C15744967 @default.
- W2012805624 hasConcept C199190896 @default.
- W2012805624 hasConcept C2780791683 @default.
- W2012805624 hasConcept C41008148 @default.
- W2012805624 hasConcept C48103436 @default.
- W2012805624 hasConcept C49937458 @default.
- W2012805624 hasConcept C62520636 @default.
- W2012805624 hasConcept C67203356 @default.
- W2012805624 hasConcept C77805123 @default.
- W2012805624 hasConcept C97541855 @default.
- W2012805624 hasConceptScore W2012805624C11413529 @default.
- W2012805624 hasConceptScore W2012805624C119857082 @default.
- W2012805624 hasConceptScore W2012805624C121332964 @default.
- W2012805624 hasConceptScore W2012805624C154945302 @default.
- W2012805624 hasConceptScore W2012805624C15744967 @default.
- W2012805624 hasConceptScore W2012805624C199190896 @default.
- W2012805624 hasConceptScore W2012805624C2780791683 @default.
- W2012805624 hasConceptScore W2012805624C41008148 @default.
- W2012805624 hasConceptScore W2012805624C48103436 @default.
- W2012805624 hasConceptScore W2012805624C49937458 @default.
- W2012805624 hasConceptScore W2012805624C62520636 @default.
- W2012805624 hasConceptScore W2012805624C67203356 @default.
- W2012805624 hasConceptScore W2012805624C77805123 @default.
- W2012805624 hasConceptScore W2012805624C97541855 @default.
- W2012805624 hasLocation W20128056241 @default.
- W2012805624 hasOpenAccess W2012805624 @default.
- W2012805624 hasPrimaryLocation W20128056241 @default.
- W2012805624 hasRelatedWork W1882507001 @default.
- W2012805624 hasRelatedWork W2134289401 @default.
- W2012805624 hasRelatedWork W2156006853 @default.
- W2012805624 hasRelatedWork W2557694176 @default.
- W2012805624 hasRelatedWork W2961085424 @default.
- W2012805624 hasRelatedWork W3022038857 @default.
- W2012805624 hasRelatedWork W3196155444 @default.
- W2012805624 hasRelatedWork W4306321456 @default.
- W2012805624 hasRelatedWork W4312812851 @default.
- W2012805624 hasRelatedWork W4319083788 @default.
- W2012805624 isParatext "false" @default.
- W2012805624 isRetracted "false" @default.
- W2012805624 magId "2012805624" @default.
- W2012805624 workType "article" @default.