Matches in SemOpenAlex for { <https://semopenalex.org/work/W2471680881> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W2471680881 abstract "REINFORCEMENT LEARNING IS THE PROCESS BY WHICH THE PROBABILITY OF THE RESPONSE OF A SYSTEM TO A STIMULUS INCREASES WITH REWARD AND DECREASES WITH PUNISHMENT [19]. MOST OF THE RESEARCH IN REINFORCEMENT LEARNING (WITH THE EXCEPTION OF THE WORK IN FUNCTION OPTIMIZATION) HAS BEEN ON PROBLEMS WITH DISCRETE ACTION SPACES, IN WHICH THE LEARNING SYSTEM CHOOSES ONE OF A FIN- ITE NUMBER OF POSSIBLE ACTIONS. HOWEVER, MANY CONTROL PROBLEMS REQUIRE THE APPLICATION OF CONTINUOUS CONTROL SIGNALS. IN THIS PAPER, WE PRESENT A STO- CHASTIC REINFORCEMENT LEARNING ALGORITHM FOR LEARNING FUNCTIONS WITH CON- TINOUS OUTPUTS. OUR ALGORITHM IS DESIGNED TO BE IMPLEMENTED AS A UNIT IN A CONNECTIONIST NETWORK. WE ASSUME THAT THE LEARNING SYSTEM COMPUTES ITS REAL -VALUED OUTPUT AS SOME FUNCTION OF A RANDOM ACTIVATION GENERATED USING THE NORMAL DISTRIBUTION. THE ACTIVATION AT ANY TIME DEPENDS ON THE TWO PARAME- TERS, THE MEAN AND THE STANDARD DEVIATION, USED IN THE NORMAL DISTRIBUTION, WHICH, IN TURN, DEPEND ON THE CURRENT INPUTS TO THE UNIT. LEARNING TAKES PLACE BY USING OUR ALGORITHM TO ADJUST THESE TWO PARAMETERS SO AS TO IN- CREASE THE PROBABILITY OF PRODUCING THE OPTIMAL REAL VALUE FOR EACH INPUT PATTERN. THE PERFORMANCE OF THE ALGORITHM IS STUDIED BY USING IT TO LEARN TASKS OF VARYING LEVELS OF DIFFICULTY. FURTHER, AS AN EXAMPLE OF A POTEN- TIAL APPLICATION, WE PRESENT A NETWORK INCORPORATING THESE REAL-VALUED UNITS THAT LEARNS THE INVERSE KINEMATIC TRANSFORM OF A SIMULATED 3 DEGREE-" @default.
- W2471680881 created "2016-07-22" @default.
- W2471680881 creator A5070071941 @default.
- W2471680881 date "1988-09-30" @default.
- W2471680881 modified "2023-09-24" @default.
- W2471680881 title "A Stochastic Algorithm for Learning Real-valued Functions via Reinforcement" @default.
- W2471680881 hasPublicationYear "1988" @default.
- W2471680881 type Work @default.
- W2471680881 sameAs 2471680881 @default.
- W2471680881 citedByCount "1" @default.
- W2471680881 crossrefType "journal-article" @default.
- W2471680881 hasAuthorship W2471680881A5070071941 @default.
- W2471680881 hasConcept C11413529 @default.
- W2471680881 hasConcept C117765406 @default.
- W2471680881 hasConcept C126255220 @default.
- W2471680881 hasConcept C154945302 @default.
- W2471680881 hasConcept C17061570 @default.
- W2471680881 hasConcept C188116033 @default.
- W2471680881 hasConcept C199190896 @default.
- W2471680881 hasConcept C33923547 @default.
- W2471680881 hasConcept C41008148 @default.
- W2471680881 hasConcept C50644808 @default.
- W2471680881 hasConcept C97541855 @default.
- W2471680881 hasConceptScore W2471680881C11413529 @default.
- W2471680881 hasConceptScore W2471680881C117765406 @default.
- W2471680881 hasConceptScore W2471680881C126255220 @default.
- W2471680881 hasConceptScore W2471680881C154945302 @default.
- W2471680881 hasConceptScore W2471680881C17061570 @default.
- W2471680881 hasConceptScore W2471680881C188116033 @default.
- W2471680881 hasConceptScore W2471680881C199190896 @default.
- W2471680881 hasConceptScore W2471680881C33923547 @default.
- W2471680881 hasConceptScore W2471680881C41008148 @default.
- W2471680881 hasConceptScore W2471680881C50644808 @default.
- W2471680881 hasConceptScore W2471680881C97541855 @default.
- W2471680881 hasLocation W24716808811 @default.
- W2471680881 hasOpenAccess W2471680881 @default.
- W2471680881 hasPrimaryLocation W24716808811 @default.
- W2471680881 hasRelatedWork W115077809 @default.
- W2471680881 hasRelatedWork W1550418129 @default.
- W2471680881 hasRelatedWork W1997816436 @default.
- W2471680881 hasRelatedWork W2025663273 @default.
- W2471680881 hasRelatedWork W2031067035 @default.
- W2471680881 hasRelatedWork W2080759927 @default.
- W2471680881 hasRelatedWork W2097031964 @default.
- W2471680881 hasRelatedWork W2115951219 @default.
- W2471680881 hasRelatedWork W2116585932 @default.
- W2471680881 hasRelatedWork W2117626647 @default.
- W2471680881 hasRelatedWork W2144655553 @default.
- W2471680881 hasRelatedWork W2152726590 @default.
- W2471680881 hasRelatedWork W2158969944 @default.
- W2471680881 hasRelatedWork W2162817713 @default.
- W2471680881 hasRelatedWork W2186564083 @default.
- W2471680881 hasRelatedWork W2573393487 @default.
- W2471680881 hasRelatedWork W2888519432 @default.
- W2471680881 hasRelatedWork W3093502037 @default.
- W2471680881 hasRelatedWork W3138738770 @default.
- W2471680881 hasRelatedWork W3165482625 @default.
- W2471680881 isParatext "false" @default.
- W2471680881 isRetracted "false" @default.
- W2471680881 magId "2471680881" @default.
- W2471680881 workType "article" @default.