Matches in SemOpenAlex for { <https://semopenalex.org/work/W2804765405> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2804765405 abstract "Although there has been remarkable progress and impressive performance on reinforcement learning (RL) on Atari games, there are many problems with challenging characteristics that have not yet been explored in Deep Learning for RL. These include reward sparsity, abrupt context-dependent reversals of strategy and time-sensitive game play. In this paper, we present Space Fortress, a game that incorporates all these characteristics and experimentally show that the presence of any of these renders state of the art Deep RL algorithms incapable of learning. Then, we present our enhancements to an existing algorithm and show big performance increases through each enhancement through an ablation study. We discuss how each of these enhancements was able to help and also argue that appropriate transfer learning boosts performance." @default.
- W2804765405 created "2018-06-01" @default.
- W2804765405 creator A5037805251 @default.
- W2804765405 creator A5079343987 @default.
- W2804765405 creator A5087505541 @default.
- W2804765405 date "2018-05-17" @default.
- W2804765405 modified "2023-09-27" @default.
- W2804765405 title "Learning Time-Sensitive Strategies in Space Fortress" @default.
- W2804765405 cites W1191599655 @default.
- W2804765405 cites W1621787170 @default.
- W2804765405 cites W1708874574 @default.
- W2804765405 cites W2000514530 @default.
- W2804765405 cites W2007286427 @default.
- W2804765405 cites W2034806191 @default.
- W2804765405 cites W2057794957 @default.
- W2804765405 cites W2097381042 @default.
- W2804765405 cites W2117539524 @default.
- W2804765405 cites W2130942839 @default.
- W2804765405 cites W2139612737 @default.
- W2804765405 cites W2145339207 @default.
- W2804765405 cites W2157331557 @default.
- W2804765405 cites W2174786457 @default.
- W2804765405 cites W2295582178 @default.
- W2804765405 cites W2335959470 @default.
- W2804765405 cites W2342662072 @default.
- W2804765405 cites W2402021148 @default.
- W2804765405 cites W2614839826 @default.
- W2804765405 cites W2736601468 @default.
- W2804765405 cites W2787037710 @default.
- W2804765405 cites W27992807 @default.
- W2804765405 cites W2962730405 @default.
- W2804765405 cites W2963276097 @default.
- W2804765405 cites W2963423916 @default.
- W2804765405 cites W2964043796 @default.
- W2804765405 hasPublicationYear "2018" @default.
- W2804765405 type Work @default.
- W2804765405 sameAs 2804765405 @default.
- W2804765405 citedByCount "0" @default.
- W2804765405 crossrefType "posted-content" @default.
- W2804765405 hasAuthorship W2804765405A5037805251 @default.
- W2804765405 hasAuthorship W2804765405A5079343987 @default.
- W2804765405 hasAuthorship W2804765405A5087505541 @default.
- W2804765405 hasConcept C108583219 @default.
- W2804765405 hasConcept C119857082 @default.
- W2804765405 hasConcept C154945302 @default.
- W2804765405 hasConcept C166957645 @default.
- W2804765405 hasConcept C2779343474 @default.
- W2804765405 hasConcept C38035415 @default.
- W2804765405 hasConcept C41008148 @default.
- W2804765405 hasConcept C95457728 @default.
- W2804765405 hasConcept C97541855 @default.
- W2804765405 hasConceptScore W2804765405C108583219 @default.
- W2804765405 hasConceptScore W2804765405C119857082 @default.
- W2804765405 hasConceptScore W2804765405C154945302 @default.
- W2804765405 hasConceptScore W2804765405C166957645 @default.
- W2804765405 hasConceptScore W2804765405C2779343474 @default.
- W2804765405 hasConceptScore W2804765405C38035415 @default.
- W2804765405 hasConceptScore W2804765405C41008148 @default.
- W2804765405 hasConceptScore W2804765405C95457728 @default.
- W2804765405 hasConceptScore W2804765405C97541855 @default.
- W2804765405 hasLocation W28047654051 @default.
- W2804765405 hasOpenAccess W2804765405 @default.
- W2804765405 hasPrimaryLocation W28047654051 @default.
- W2804765405 hasRelatedWork W2550182557 @default.
- W2804765405 hasRelatedWork W2755614540 @default.
- W2804765405 hasRelatedWork W2773252567 @default.
- W2804765405 hasRelatedWork W2787993599 @default.
- W2804765405 hasRelatedWork W2805560727 @default.
- W2804765405 hasRelatedWork W2892056821 @default.
- W2804765405 hasRelatedWork W2904338767 @default.
- W2804765405 hasRelatedWork W2909395135 @default.
- W2804765405 hasRelatedWork W2964263543 @default.
- W2804765405 hasRelatedWork W2976657239 @default.
- W2804765405 hasRelatedWork W2982365794 @default.
- W2804765405 hasRelatedWork W2989957090 @default.
- W2804765405 hasRelatedWork W2997475283 @default.
- W2804765405 hasRelatedWork W2999374227 @default.
- W2804765405 hasRelatedWork W3081661003 @default.
- W2804765405 hasRelatedWork W3105335800 @default.
- W2804765405 hasRelatedWork W3126558058 @default.
- W2804765405 hasRelatedWork W3131806378 @default.
- W2804765405 hasRelatedWork W3160722708 @default.
- W2804765405 hasRelatedWork W3173061714 @default.
- W2804765405 isParatext "false" @default.
- W2804765405 isRetracted "false" @default.
- W2804765405 magId "2804765405" @default.
- W2804765405 workType "article" @default.