Matches in SemOpenAlex for { <https://semopenalex.org/work/W3015411832> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3015411832 abstract "Potential Based Reward Shaping combined with a potential function based on appropriately defined abstract knowledge has been shown to significantly improve learning speed in Reinforcement Learning. MultiGrid Reinforcement Learning (MRL) has further shown that such abstract knowledge in the form of a potential function can be learned almost solely from agent interaction with the environment. However, we show that MRL faces the problem of not extending well to work with Deep Learning. In this paper we extend and improve MRL to take advantage of modern Deep Learning algorithms such as Deep Q-Networks (DQN). We show that DQN augmented with our approach perform significantly better on continuous control tasks than its Vanilla counterpart and DQN augmented with MRL." @default.
- W3015411832 created "2020-04-17" @default.
- W3015411832 creator A5009587907 @default.
- W3015411832 creator A5044048765 @default.
- W3015411832 date "2020-04-06" @default.
- W3015411832 modified "2023-09-27" @default.
- W3015411832 title "Uniform State Abstraction For Reinforcement Learning" @default.
- W3015411832 cites W1499408472 @default.
- W3015411832 cites W1515851193 @default.
- W3015411832 cites W1553476745 @default.
- W3015411832 cites W1757796397 @default.
- W3015411832 cites W1777239053 @default.
- W3015411832 cites W1980648727 @default.
- W3015411832 cites W1981096006 @default.
- W3015411832 cites W1985756506 @default.
- W3015411832 cites W1988821219 @default.
- W3015411832 cites W2080379318 @default.
- W3015411832 cites W2082973084 @default.
- W3015411832 cites W2109910161 @default.
- W3015411832 cites W2111316871 @default.
- W3015411832 cites W2158969944 @default.
- W3015411832 cites W2160808139 @default.
- W3015411832 cites W2182079046 @default.
- W3015411832 cites W2250340166 @default.
- W3015411832 cites W2335959470 @default.
- W3015411832 cites W2402540331 @default.
- W3015411832 cites W2754926205 @default.
- W3015411832 cites W2762254752 @default.
- W3015411832 hasPublicationYear "2020" @default.
- W3015411832 type Work @default.
- W3015411832 sameAs 3015411832 @default.
- W3015411832 citedByCount "0" @default.
- W3015411832 crossrefType "posted-content" @default.
- W3015411832 hasAuthorship W3015411832A5009587907 @default.
- W3015411832 hasAuthorship W3015411832A5044048765 @default.
- W3015411832 hasConcept C111472728 @default.
- W3015411832 hasConcept C11413529 @default.
- W3015411832 hasConcept C119857082 @default.
- W3015411832 hasConcept C124304363 @default.
- W3015411832 hasConcept C138885662 @default.
- W3015411832 hasConcept C14036430 @default.
- W3015411832 hasConcept C154945302 @default.
- W3015411832 hasConcept C2775924081 @default.
- W3015411832 hasConcept C41008148 @default.
- W3015411832 hasConcept C48103436 @default.
- W3015411832 hasConcept C78458016 @default.
- W3015411832 hasConcept C86803240 @default.
- W3015411832 hasConcept C97541855 @default.
- W3015411832 hasConceptScore W3015411832C111472728 @default.
- W3015411832 hasConceptScore W3015411832C11413529 @default.
- W3015411832 hasConceptScore W3015411832C119857082 @default.
- W3015411832 hasConceptScore W3015411832C124304363 @default.
- W3015411832 hasConceptScore W3015411832C138885662 @default.
- W3015411832 hasConceptScore W3015411832C14036430 @default.
- W3015411832 hasConceptScore W3015411832C154945302 @default.
- W3015411832 hasConceptScore W3015411832C2775924081 @default.
- W3015411832 hasConceptScore W3015411832C41008148 @default.
- W3015411832 hasConceptScore W3015411832C48103436 @default.
- W3015411832 hasConceptScore W3015411832C78458016 @default.
- W3015411832 hasConceptScore W3015411832C86803240 @default.
- W3015411832 hasConceptScore W3015411832C97541855 @default.
- W3015411832 hasLocation W30154118321 @default.
- W3015411832 hasOpenAccess W3015411832 @default.
- W3015411832 hasPrimaryLocation W30154118321 @default.
- W3015411832 hasRelatedWork W1553476745 @default.
- W3015411832 hasRelatedWork W1982948368 @default.
- W3015411832 hasRelatedWork W2194966727 @default.
- W3015411832 hasRelatedWork W2290354866 @default.
- W3015411832 hasRelatedWork W2369463503 @default.
- W3015411832 hasRelatedWork W2428834750 @default.
- W3015411832 hasRelatedWork W2491675558 @default.
- W3015411832 hasRelatedWork W2553109721 @default.
- W3015411832 hasRelatedWork W2792645523 @default.
- W3015411832 hasRelatedWork W2798338638 @default.
- W3015411832 hasRelatedWork W2910568379 @default.
- W3015411832 hasRelatedWork W2982852993 @default.
- W3015411832 hasRelatedWork W2997368604 @default.
- W3015411832 hasRelatedWork W3037179286 @default.
- W3015411832 hasRelatedWork W3047690370 @default.
- W3015411832 hasRelatedWork W3090555890 @default.
- W3015411832 hasRelatedWork W3167613675 @default.
- W3015411832 hasRelatedWork W3184387694 @default.
- W3015411832 hasRelatedWork W3198061585 @default.
- W3015411832 hasRelatedWork W3203418126 @default.
- W3015411832 isParatext "false" @default.
- W3015411832 isRetracted "false" @default.
- W3015411832 magId "3015411832" @default.
- W3015411832 workType "article" @default.