Matches in SemOpenAlex for { <https://semopenalex.org/work/W2975052530> ?p ?o ?g. }
Showing items 1 to 48 of
48
with 100 items per page.
- W2975052530 abstract "ViZDoom is an infamous first-person shooter game. Several studies have been conducted to develop agents that can automatically complete game tasks using a reinforcement learning algorithm. Although these studies yielded substantial progress, models proposed by the previous studies when applied to the my way home scenario in ViZDoom presented two problems. The first one is that when an agent walks into a specific room, it appears to be immobile and although it does not move until the time ends, the view constantly changes from left to right. The second problem is the slow learning speed of the model. To address these issues, a time penalty method and a modified neural network construction method are proposed in this study. The experimental results demonstrate that the addition of a time penalty improved the learning rate by 40% compared to the methods in which time penalty was not added. Moreover, the models proposed in previous studies could complete only 73% to 85% of the tasks, whereas the method proposed herein can complete 100% of the tasks." @default.
- W2975052530 created "2019-10-03" @default.
- W2975052530 creator A5013930439 @default.
- W2975052530 creator A5050857532 @default.
- W2975052530 date "2019-08-01" @default.
- W2975052530 modified "2023-10-16" @default.
- W2975052530 title "Modified PPO-RND Method for Solving Sparse Reward Problem in ViZDoom" @default.
- W2975052530 cites W2963473082 @default.
- W2975052530 cites W2963523627 @default.
- W2975052530 doi "https://doi.org/10.1109/cig.2019.8847999" @default.
- W2975052530 hasPublicationYear "2019" @default.
- W2975052530 type Work @default.
- W2975052530 sameAs 2975052530 @default.
- W2975052530 citedByCount "2" @default.
- W2975052530 countsByYear W29750525302021 @default.
- W2975052530 countsByYear W29750525302023 @default.
- W2975052530 crossrefType "proceedings-article" @default.
- W2975052530 hasAuthorship W2975052530A5013930439 @default.
- W2975052530 hasAuthorship W2975052530A5050857532 @default.
- W2975052530 hasConcept C119857082 @default.
- W2975052530 hasConcept C154945302 @default.
- W2975052530 hasConcept C188116033 @default.
- W2975052530 hasConcept C41008148 @default.
- W2975052530 hasConcept C50644808 @default.
- W2975052530 hasConcept C97541855 @default.
- W2975052530 hasConceptScore W2975052530C119857082 @default.
- W2975052530 hasConceptScore W2975052530C154945302 @default.
- W2975052530 hasConceptScore W2975052530C188116033 @default.
- W2975052530 hasConceptScore W2975052530C41008148 @default.
- W2975052530 hasConceptScore W2975052530C50644808 @default.
- W2975052530 hasConceptScore W2975052530C97541855 @default.
- W2975052530 hasLocation W29750525301 @default.
- W2975052530 hasOpenAccess W2975052530 @default.
- W2975052530 hasPrimaryLocation W29750525301 @default.
- W2975052530 hasRelatedWork W2154793587 @default.
- W2975052530 hasRelatedWork W2951071805 @default.
- W2975052530 hasRelatedWork W2961085424 @default.
- W2975052530 hasRelatedWork W3005560120 @default.
- W2975052530 hasRelatedWork W3022038857 @default.
- W2975052530 hasRelatedWork W3209094908 @default.
- W2975052530 hasRelatedWork W4206669594 @default.
- W2975052530 hasRelatedWork W4210912933 @default.
- W2975052530 hasRelatedWork W4319083788 @default.
- W2975052530 hasRelatedWork W1629725936 @default.
- W2975052530 isParatext "false" @default.
- W2975052530 isRetracted "false" @default.
- W2975052530 magId "2975052530" @default.
- W2975052530 workType "article" @default.