Matches in SemOpenAlex for { <https://semopenalex.org/work/W2913906356> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2913906356 endingPage "186" @default.
- W2913906356 startingPage "177" @default.
- W2913906356 abstract "This paper is a report of our extensive experimentation, during the last two years, of deep reinforcement techniques for training an agent to move in the dungeons of the famous Rogue video game. The challenging nature of the problem is tightly related to the procedural, random generation of new dungeon maps at each level, which forbids any form of level-specific learning and forces us to address the navigation problem in its full generality. Other interesting aspects of the game from the point of view of automatic learning are the partially observable nature of the problem since maps are initially not visible and get discovered during exploration, and the problem of sparse rewards, requiring the acquisition of complex, nonreactive behaviors involving memory and planning. In this paper, we develop on previous works to make a more systematic comparison of different learning techniques, focusing in particular on Asynchronous Advantage Actor–Critic and Actor–Critic with Experience Replay (ACER). In a game like Rogue , sparsity of rewards is mitigated by the variability of the dungeon configurations (sometimes, by luck, exit is at hand); if this variability can be tamed—as ACER, better than other algorithms, seems able to do—the problem of sparse rewards can be overcome without any need of intrinsic motivations." @default.
- W2913906356 created "2019-02-21" @default.
- W2913906356 creator A5032765727 @default.
- W2913906356 creator A5049804104 @default.
- W2913906356 creator A5056310041 @default.
- W2913906356 creator A5073146250 @default.
- W2913906356 creator A5084097737 @default.
- W2913906356 date "2020-06-01" @default.
- W2913906356 modified "2023-09-29" @default.
- W2913906356 title "Crawling in Rogue's Dungeons With Deep Reinforcement Techniques" @default.
- W2913906356 cites W1528749982 @default.
- W2913906356 cites W1556824961 @default.
- W2913906356 cites W1591713425 @default.
- W2913906356 cites W2109910161 @default.
- W2913906356 cites W2145339207 @default.
- W2913906356 cites W2963871073 @default.
- W2913906356 cites W3099072486 @default.
- W2913906356 cites W3103780890 @default.
- W2913906356 doi "https://doi.org/10.1109/tg.2019.2899159" @default.
- W2913906356 hasPublicationYear "2020" @default.
- W2913906356 type Work @default.
- W2913906356 sameAs 2913906356 @default.
- W2913906356 citedByCount "6" @default.
- W2913906356 countsByYear W29139063562019 @default.
- W2913906356 countsByYear W29139063562020 @default.
- W2913906356 countsByYear W29139063562021 @default.
- W2913906356 countsByYear W29139063562023 @default.
- W2913906356 crossrefType "journal-article" @default.
- W2913906356 hasAuthorship W2913906356A5032765727 @default.
- W2913906356 hasAuthorship W2913906356A5049804104 @default.
- W2913906356 hasAuthorship W2913906356A5056310041 @default.
- W2913906356 hasAuthorship W2913906356A5073146250 @default.
- W2913906356 hasAuthorship W2913906356A5084097737 @default.
- W2913906356 hasConcept C100368936 @default.
- W2913906356 hasConcept C105702510 @default.
- W2913906356 hasConcept C154945302 @default.
- W2913906356 hasConcept C15744967 @default.
- W2913906356 hasConcept C41008148 @default.
- W2913906356 hasConcept C67203356 @default.
- W2913906356 hasConcept C77805123 @default.
- W2913906356 hasConcept C86803240 @default.
- W2913906356 hasConceptScore W2913906356C100368936 @default.
- W2913906356 hasConceptScore W2913906356C105702510 @default.
- W2913906356 hasConceptScore W2913906356C154945302 @default.
- W2913906356 hasConceptScore W2913906356C15744967 @default.
- W2913906356 hasConceptScore W2913906356C41008148 @default.
- W2913906356 hasConceptScore W2913906356C67203356 @default.
- W2913906356 hasConceptScore W2913906356C77805123 @default.
- W2913906356 hasConceptScore W2913906356C86803240 @default.
- W2913906356 hasIssue "2" @default.
- W2913906356 hasLocation W29139063561 @default.
- W2913906356 hasOpenAccess W2913906356 @default.
- W2913906356 hasPrimaryLocation W29139063561 @default.
- W2913906356 hasRelatedWork W1492500749 @default.
- W2913906356 hasRelatedWork W1529638493 @default.
- W2913906356 hasRelatedWork W2062419209 @default.
- W2913906356 hasRelatedWork W2078475175 @default.
- W2913906356 hasRelatedWork W2319283426 @default.
- W2913906356 hasRelatedWork W2358547986 @default.
- W2913906356 hasRelatedWork W2558137253 @default.
- W2913906356 hasRelatedWork W2795026818 @default.
- W2913906356 hasRelatedWork W3107474891 @default.
- W2913906356 hasRelatedWork W3204104695 @default.
- W2913906356 hasVolume "12" @default.
- W2913906356 isParatext "false" @default.
- W2913906356 isRetracted "false" @default.
- W2913906356 magId "2913906356" @default.
- W2913906356 workType "article" @default.