Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950262012> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W2950262012 abstract "In this work we present a method for using Deep Q-Networks (DQNs) in multi-objective environments. Deep Q-Networks provide remarkable performance in single objective problems learning from high-level visual state representations. However, in many scenarios (e.g in robotics, games), the agent needs to pursue multiple objectives simultaneously. We propose an architecture in which separate DQNs are used to control the agent's behaviour with respect to particular objectives. In this architecture we introduce decision values to improve the scalarization of multiple DQNs into a single action. Our architecture enables the decomposition of the agent's behaviour into controllable and replaceable sub-behaviours learned by distinct modules. Moreover, it allows to change the priorities of particular objectives post-learning, while preserving the overall performance of the agent. To evaluate our solution we used a game-like simulator in which an agent - provided with high-level visual input - pursues multiple objectives in a 2D world." @default.
- W2950262012 created "2019-06-27" @default.
- W2950262012 creator A5027080461 @default.
- W2950262012 date "2017-04-21" @default.
- W2950262012 modified "2023-09-27" @default.
- W2950262012 title "Modular Multi-Objective Deep Reinforcement Learning with Decision Values" @default.
- W2950262012 cites W1515851193 @default.
- W2950262012 cites W1541273733 @default.
- W2950262012 cites W1757796397 @default.
- W2950262012 cites W1987725948 @default.
- W2950262012 cites W2002305926 @default.
- W2950262012 cites W2060846151 @default.
- W2950262012 cites W2082709276 @default.
- W2950262012 cites W2097856935 @default.
- W2950262012 cites W2113226229 @default.
- W2950262012 cites W2141481921 @default.
- W2950262012 cites W2145339207 @default.
- W2950262012 cites W2173564293 @default.
- W2950262012 cites W2186820913 @default.
- W2950262012 cites W2201581102 @default.
- W2950262012 cites W2339009915 @default.
- W2950262012 cites W2530195778 @default.
- W2950262012 cites W72400652 @default.
- W2950262012 cites W3089091950 @default.
- W2950262012 hasPublicationYear "2017" @default.
- W2950262012 type Work @default.
- W2950262012 sameAs 2950262012 @default.
- W2950262012 citedByCount "0" @default.
- W2950262012 crossrefType "posted-content" @default.
- W2950262012 hasAuthorship W2950262012A5027080461 @default.
- W2950262012 hasConcept C101468663 @default.
- W2950262012 hasConcept C108583219 @default.
- W2950262012 hasConcept C119857082 @default.
- W2950262012 hasConcept C121332964 @default.
- W2950262012 hasConcept C123657996 @default.
- W2950262012 hasConcept C124681953 @default.
- W2950262012 hasConcept C142362112 @default.
- W2950262012 hasConcept C153349607 @default.
- W2950262012 hasConcept C154945302 @default.
- W2950262012 hasConcept C18903297 @default.
- W2950262012 hasConcept C199360897 @default.
- W2950262012 hasConcept C2775924081 @default.
- W2950262012 hasConcept C2780791683 @default.
- W2950262012 hasConcept C34413123 @default.
- W2950262012 hasConcept C41008148 @default.
- W2950262012 hasConcept C48103436 @default.
- W2950262012 hasConcept C62520636 @default.
- W2950262012 hasConcept C86803240 @default.
- W2950262012 hasConcept C90509273 @default.
- W2950262012 hasConcept C97541855 @default.
- W2950262012 hasConceptScore W2950262012C101468663 @default.
- W2950262012 hasConceptScore W2950262012C108583219 @default.
- W2950262012 hasConceptScore W2950262012C119857082 @default.
- W2950262012 hasConceptScore W2950262012C121332964 @default.
- W2950262012 hasConceptScore W2950262012C123657996 @default.
- W2950262012 hasConceptScore W2950262012C124681953 @default.
- W2950262012 hasConceptScore W2950262012C142362112 @default.
- W2950262012 hasConceptScore W2950262012C153349607 @default.
- W2950262012 hasConceptScore W2950262012C154945302 @default.
- W2950262012 hasConceptScore W2950262012C18903297 @default.
- W2950262012 hasConceptScore W2950262012C199360897 @default.
- W2950262012 hasConceptScore W2950262012C2775924081 @default.
- W2950262012 hasConceptScore W2950262012C2780791683 @default.
- W2950262012 hasConceptScore W2950262012C34413123 @default.
- W2950262012 hasConceptScore W2950262012C41008148 @default.
- W2950262012 hasConceptScore W2950262012C48103436 @default.
- W2950262012 hasConceptScore W2950262012C62520636 @default.
- W2950262012 hasConceptScore W2950262012C86803240 @default.
- W2950262012 hasConceptScore W2950262012C90509273 @default.
- W2950262012 hasConceptScore W2950262012C97541855 @default.
- W2950262012 hasLocation W29502620121 @default.
- W2950262012 hasOpenAccess W2950262012 @default.
- W2950262012 hasPrimaryLocation W29502620121 @default.
- W2950262012 hasRelatedWork W126344362 @default.
- W2950262012 hasRelatedWork W1504806788 @default.
- W2950262012 hasRelatedWork W1563670688 @default.
- W2950262012 hasRelatedWork W1594545887 @default.
- W2950262012 hasRelatedWork W2006303459 @default.
- W2950262012 hasRelatedWork W2034252760 @default.
- W2950262012 hasRelatedWork W2237185708 @default.
- W2950262012 hasRelatedWork W2395575420 @default.
- W2950262012 hasRelatedWork W2398676732 @default.
- W2950262012 hasRelatedWork W2409817223 @default.
- W2950262012 hasRelatedWork W2788058077 @default.
- W2950262012 hasRelatedWork W2795688094 @default.
- W2950262012 hasRelatedWork W3014503118 @default.
- W2950262012 hasRelatedWork W3037793033 @default.
- W2950262012 hasRelatedWork W3098297242 @default.
- W2950262012 hasRelatedWork W3098974658 @default.
- W2950262012 hasRelatedWork W3100019413 @default.
- W2950262012 hasRelatedWork W3112808542 @default.
- W2950262012 hasRelatedWork W3198198069 @default.
- W2950262012 hasRelatedWork W3200101246 @default.
- W2950262012 isParatext "false" @default.
- W2950262012 isRetracted "false" @default.
- W2950262012 magId "2950262012" @default.
- W2950262012 workType "article" @default.