FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W193076044> ?p ?o ?g. }

• W193076044 endingPage "1217" @default.
• W193076044 startingPage "1211" @default.
• W193076044 abstract "In this paper we propose to combine three AI techniques to speed up a Reinforcement Learning algorithm in a Transfer Learning problem: Case-based Reasoning, Heuristically Accelerated Reinforcement Learning and Neural Networks. To do so, we propose a new algorithm, called L3, which works in 3 stages: in the first stage, it uses Reinforcement Learning to learn how to perform one task, and stores the optimal policy for this problem as a case-base; in the second stage, it uses a Neural Network to map actions from one domain to actions in the other domain and; in the third stage, it uses the case-base learned in the first stage as heuristics to speed up the learning performance in a related, but different, task. The RL algorithm used in the first phase is the Q-learning and in the third phase is the recently proposed Case-based Heuristically Accelerated Q-learning. A set of empirical evaluations were conducted in transferring the learning between two domains, the Acrobot and the Robocup 3D: the policy learned during the solution of the Acrobot Problem is transferred and used to speed up the learning of stability policies for a humanoid robot in the Robocup 3D simulator. The results show that the use of this algorithm can lead to a significant improvement in the performance of the agent." @default.
• W193076044 created "2016-06-24" @default.
• W193076044 creator A5073156082 @default.
• W193076044 creator A5074028327 @default.
• W193076044 creator A5074815589 @default.
• W193076044 creator A5075585541 @default.
• W193076044 date "2011-07-16" @default.
• W193076044 modified "2023-10-18" @default.
• W193076044 title "Using cases as heuristics in reinforcement learning: a transfer learning application" @default.
• W193076044 cites W10379689 @default.
• W193076044 cites W1502099479 @default.
• W193076044 cites W1515851193 @default.
• W193076044 cites W1559035773 @default.
• W193076044 cites W1592209052 @default.
• W193076044 cites W1817398672 @default.
• W193076044 cites W1993277309 @default.
• W193076044 cites W2004030284 @default.
• W193076044 cites W2031727428 @default.
• W193076044 cites W2076766268 @default.
• W193076044 cites W2095182442 @default.
• W193076044 cites W2097381042 @default.
• W193076044 cites W2100726628 @default.
• W193076044 cites W2106953752 @default.
• W193076044 cites W2110292307 @default.
• W193076044 cites W2121863487 @default.
• W193076044 cites W2151340488 @default.
• W193076044 cites W2153353285 @default.
• W193076044 cites W2163808368 @default.
• W193076044 cites W2166798247 @default.
• W193076044 cites W3011120880 @default.
• W193076044 cites W36691172 @default.
• W193076044 cites W90468634 @default.
• W193076044 doi "https://doi.org/10.5591/978-1-57735-516-8/ijcai11-206" @default.
• W193076044 hasPublicationYear "2011" @default.
• W193076044 type Work @default.
• W193076044 sameAs 193076044 @default.
• W193076044 citedByCount "12" @default.
• W193076044 countsByYear W1930760442012 @default.
• W193076044 countsByYear W1930760442013 @default.
• W193076044 countsByYear W1930760442014 @default.
• W193076044 countsByYear W1930760442015 @default.
• W193076044 countsByYear W1930760442017 @default.
• W193076044 countsByYear W1930760442018 @default.
• W193076044 countsByYear W1930760442020 @default.
• W193076044 countsByYear W1930760442021 @default.
• W193076044 crossrefType "proceedings-article" @default.
• W193076044 hasAuthorship W193076044A5073156082 @default.
• W193076044 hasAuthorship W193076044A5074028327 @default.
• W193076044 hasAuthorship W193076044A5074815589 @default.
• W193076044 hasAuthorship W193076044A5075585541 @default.
• W193076044 hasConcept C111919701 @default.
• W193076044 hasConcept C112972136 @default.
• W193076044 hasConcept C119857082 @default.
• W193076044 hasConcept C127413603 @default.
• W193076044 hasConcept C127705205 @default.
• W193076044 hasConcept C134306372 @default.
• W193076044 hasConcept C150899416 @default.
• W193076044 hasConcept C154945302 @default.
• W193076044 hasConcept C177264268 @default.
• W193076044 hasConcept C188888258 @default.
• W193076044 hasConcept C199190896 @default.
• W193076044 hasConcept C199360897 @default.
• W193076044 hasConcept C19966478 @default.
• W193076044 hasConcept C201995342 @default.
• W193076044 hasConcept C2780451532 @default.
• W193076044 hasConcept C28006648 @default.
• W193076044 hasConcept C33923547 @default.
• W193076044 hasConcept C36503486 @default.
• W193076044 hasConcept C41008148 @default.
• W193076044 hasConcept C50644808 @default.
• W193076044 hasConcept C90509273 @default.
• W193076044 hasConcept C97541855 @default.
• W193076044 hasConceptScore W193076044C111919701 @default.
• W193076044 hasConceptScore W193076044C112972136 @default.
• W193076044 hasConceptScore W193076044C119857082 @default.
• W193076044 hasConceptScore W193076044C127413603 @default.
• W193076044 hasConceptScore W193076044C127705205 @default.
• W193076044 hasConceptScore W193076044C134306372 @default.
• W193076044 hasConceptScore W193076044C150899416 @default.
• W193076044 hasConceptScore W193076044C154945302 @default.
• W193076044 hasConceptScore W193076044C177264268 @default.
• W193076044 hasConceptScore W193076044C188888258 @default.
• W193076044 hasConceptScore W193076044C199190896 @default.
• W193076044 hasConceptScore W193076044C199360897 @default.
• W193076044 hasConceptScore W193076044C19966478 @default.
• W193076044 hasConceptScore W193076044C201995342 @default.
• W193076044 hasConceptScore W193076044C2780451532 @default.
• W193076044 hasConceptScore W193076044C28006648 @default.
• W193076044 hasConceptScore W193076044C33923547 @default.
• W193076044 hasConceptScore W193076044C36503486 @default.
• W193076044 hasConceptScore W193076044C41008148 @default.
• W193076044 hasConceptScore W193076044C50644808 @default.
• W193076044 hasConceptScore W193076044C90509273 @default.
• W193076044 hasConceptScore W193076044C97541855 @default.
• W193076044 hasLocation W1930760441 @default.
• W193076044 hasOpenAccess W193076044 @default.
• W193076044 hasPrimaryLocation W1930760441 @default.
• W193076044 hasRelatedWork W1997816436 @default.

• next