Matches in SemOpenAlex for { <https://semopenalex.org/work/W2753176368> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2753176368 abstract "Artificial intelligence (AI) agent created with Deep Q-Networks (DQN) can defeat human agents in video games. Despite its high performance, DQN often exhibits odd behaviors, which could be immersion-breaking against the purpose of creating game AI. Moreover, DQN is capable of reacting to the game environment much faster than humans, making itself invincible (thus not fun to play with) in certain types of games. On the other hand, supervised learning framework trains an AI agent using historical play data of human agents as training data. Supervised learning agent exhibits a more human-like behavior than reinforcement learning agents because of imitating training data. However, its performance is often no better than human agents. The ultimate purpose of AI agents is to entertain human players. A good performance and a humanlike behavior are important factors of the AI agents, and both of them should be achieved simultaneously. This study proposes frameworks combining reinforcement learning and supervised learning and we call then separated network model and shared network model. We evaluated their performances by the game scores and behaviors by Turing test. The experimental results demonstrate that the proposed frameworks develop an AI agent of better performance than human agent and natural behavior than reinforcement learning agents." @default.
- W2753176368 created "2017-09-15" @default.
- W2753176368 creator A5023847482 @default.
- W2753176368 creator A5039694783 @default.
- W2753176368 creator A5039845750 @default.
- W2753176368 creator A5064218476 @default.
- W2753176368 creator A5068667478 @default.
- W2753176368 date "2017-06-01" @default.
- W2753176368 modified "2023-09-24" @default.
- W2753176368 title "Developing game AI agent behaving like human by mixing reinforcement learning and supervised learning" @default.
- W2753176368 cites W1522301498 @default.
- W2753176368 cites W1557517019 @default.
- W2753176368 cites W1574691582 @default.
- W2753176368 cites W2001771035 @default.
- W2753176368 cites W2016053056 @default.
- W2753176368 cites W2026485182 @default.
- W2753176368 cites W2041224215 @default.
- W2753176368 cites W2098535914 @default.
- W2753176368 cites W2141559645 @default.
- W2753176368 cites W2145339207 @default.
- W2753176368 cites W2156387975 @default.
- W2753176368 cites W2163605009 @default.
- W2753176368 cites W2164128966 @default.
- W2753176368 cites W2182734678 @default.
- W2753176368 cites W2291634899 @default.
- W2753176368 cites W2546302380 @default.
- W2753176368 cites W2737560561 @default.
- W2753176368 cites W2914656440 @default.
- W2753176368 cites W32403112 @default.
- W2753176368 cites W656377046 @default.
- W2753176368 doi "https://doi.org/10.1109/snpd.2017.8022767" @default.
- W2753176368 hasPublicationYear "2017" @default.
- W2753176368 type Work @default.
- W2753176368 sameAs 2753176368 @default.
- W2753176368 citedByCount "3" @default.
- W2753176368 countsByYear W27531763682018 @default.
- W2753176368 countsByYear W27531763682019 @default.
- W2753176368 countsByYear W27531763682022 @default.
- W2753176368 crossrefType "proceedings-article" @default.
- W2753176368 hasAuthorship W2753176368A5023847482 @default.
- W2753176368 hasAuthorship W2753176368A5039694783 @default.
- W2753176368 hasAuthorship W2753176368A5039845750 @default.
- W2753176368 hasAuthorship W2753176368A5064218476 @default.
- W2753176368 hasAuthorship W2753176368A5068667478 @default.
- W2753176368 hasConcept C119857082 @default.
- W2753176368 hasConcept C154945302 @default.
- W2753176368 hasConcept C15744967 @default.
- W2753176368 hasConcept C41008148 @default.
- W2753176368 hasConcept C50644808 @default.
- W2753176368 hasConcept C577917 @default.
- W2753176368 hasConcept C67203356 @default.
- W2753176368 hasConcept C77805123 @default.
- W2753176368 hasConcept C97541855 @default.
- W2753176368 hasConceptScore W2753176368C119857082 @default.
- W2753176368 hasConceptScore W2753176368C154945302 @default.
- W2753176368 hasConceptScore W2753176368C15744967 @default.
- W2753176368 hasConceptScore W2753176368C41008148 @default.
- W2753176368 hasConceptScore W2753176368C50644808 @default.
- W2753176368 hasConceptScore W2753176368C577917 @default.
- W2753176368 hasConceptScore W2753176368C67203356 @default.
- W2753176368 hasConceptScore W2753176368C77805123 @default.
- W2753176368 hasConceptScore W2753176368C97541855 @default.
- W2753176368 hasLocation W27531763681 @default.
- W2753176368 hasOpenAccess W2753176368 @default.
- W2753176368 hasPrimaryLocation W27531763681 @default.
- W2753176368 hasRelatedWork W1994875077 @default.
- W2753176368 hasRelatedWork W2070627246 @default.
- W2753176368 hasRelatedWork W2113711557 @default.
- W2753176368 hasRelatedWork W2128867011 @default.
- W2753176368 hasRelatedWork W2142600926 @default.
- W2753176368 hasRelatedWork W2147071026 @default.
- W2753176368 hasRelatedWork W2157175320 @default.
- W2753176368 hasRelatedWork W2563112808 @default.
- W2753176368 hasRelatedWork W2740671916 @default.
- W2753176368 hasRelatedWork W2771590356 @default.
- W2753176368 hasRelatedWork W2889665471 @default.
- W2753176368 hasRelatedWork W2912943342 @default.
- W2753176368 hasRelatedWork W2922485250 @default.
- W2753176368 hasRelatedWork W2944710665 @default.
- W2753176368 hasRelatedWork W2963890729 @default.
- W2753176368 hasRelatedWork W2979210969 @default.
- W2753176368 hasRelatedWork W3018569081 @default.
- W2753176368 hasRelatedWork W3111442723 @default.
- W2753176368 hasRelatedWork W3118726239 @default.
- W2753176368 hasRelatedWork W3213159396 @default.
- W2753176368 isParatext "false" @default.
- W2753176368 isRetracted "false" @default.
- W2753176368 magId "2753176368" @default.
- W2753176368 workType "article" @default.