Matches in SemOpenAlex for { <https://semopenalex.org/work/W2004019504> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W2004019504 abstract "Temporal difference learning methods have been successfully applied to a wide range of stochastic learning and control problems. In addition to correctness, one metric of a technique's performance is its learning rate - the number of iterations required to converge to an optimal solution. The learning rate can be increased by using multiple agents that can share experience. In a software environment, the potential speedup from additional agents is limited, since adding agents significantly increases the burden of computation and/or hinders real-time processing. To address this problem, this paper presents a parameterized hardware model of a multi-agent system based on a shared-memory Symmetric Multiprocessor (SMP). To the author's knowledge, this is the first application of an SMP architecture to a multi-agent reinforcement learning system. The control model employed is a multi-agent variation of the Sarsa(?) algorithm. Several hardware optimizations schemes are investigated with respect to feasibility and expected performance. The system is modeled using a cycle-accurate simulation in SystemC. The results indicate that real-time learning rates can be significantly improved by employing the proposed parallel hardware implementation." @default.
- W2004019504 created "2016-06-24" @default.
- W2004019504 creator A5007748902 @default.
- W2004019504 creator A5063480258 @default.
- W2004019504 date "2006-08-01" @default.
- W2004019504 modified "2023-09-25" @default.
- W2004019504 title "A Symmetric Multiprocessor Architecture for Multi-Agent Temporal Difference Learning" @default.
- W2004019504 cites W1849208822 @default.
- W2004019504 cites W2121863487 @default.
- W2004019504 cites W2139653418 @default.
- W2004019504 cites W2166297784 @default.
- W2004019504 cites W2915494090 @default.
- W2004019504 doi "https://doi.org/10.1109/mwscas.2006.382109" @default.
- W2004019504 hasPublicationYear "2006" @default.
- W2004019504 type Work @default.
- W2004019504 sameAs 2004019504 @default.
- W2004019504 citedByCount "1" @default.
- W2004019504 crossrefType "proceedings-article" @default.
- W2004019504 hasAuthorship W2004019504A5007748902 @default.
- W2004019504 hasAuthorship W2004019504A5063480258 @default.
- W2004019504 hasConcept C11413529 @default.
- W2004019504 hasConcept C154945302 @default.
- W2004019504 hasConcept C162324750 @default.
- W2004019504 hasConcept C165464430 @default.
- W2004019504 hasConcept C173608175 @default.
- W2004019504 hasConcept C176217482 @default.
- W2004019504 hasConcept C196340769 @default.
- W2004019504 hasConcept C21547014 @default.
- W2004019504 hasConcept C41008148 @default.
- W2004019504 hasConcept C45374587 @default.
- W2004019504 hasConcept C4822641 @default.
- W2004019504 hasConcept C55439883 @default.
- W2004019504 hasConcept C68339613 @default.
- W2004019504 hasConcept C97541855 @default.
- W2004019504 hasConceptScore W2004019504C11413529 @default.
- W2004019504 hasConceptScore W2004019504C154945302 @default.
- W2004019504 hasConceptScore W2004019504C162324750 @default.
- W2004019504 hasConceptScore W2004019504C165464430 @default.
- W2004019504 hasConceptScore W2004019504C173608175 @default.
- W2004019504 hasConceptScore W2004019504C176217482 @default.
- W2004019504 hasConceptScore W2004019504C196340769 @default.
- W2004019504 hasConceptScore W2004019504C21547014 @default.
- W2004019504 hasConceptScore W2004019504C41008148 @default.
- W2004019504 hasConceptScore W2004019504C45374587 @default.
- W2004019504 hasConceptScore W2004019504C4822641 @default.
- W2004019504 hasConceptScore W2004019504C55439883 @default.
- W2004019504 hasConceptScore W2004019504C68339613 @default.
- W2004019504 hasConceptScore W2004019504C97541855 @default.
- W2004019504 hasLocation W20040195041 @default.
- W2004019504 hasOpenAccess W2004019504 @default.
- W2004019504 hasPrimaryLocation W20040195041 @default.
- W2004019504 hasRelatedWork W1517776641 @default.
- W2004019504 hasRelatedWork W1525693705 @default.
- W2004019504 hasRelatedWork W1577207287 @default.
- W2004019504 hasRelatedWork W2079959934 @default.
- W2004019504 hasRelatedWork W2805154545 @default.
- W2004019504 hasRelatedWork W300950598 @default.
- W2004019504 hasRelatedWork W4252830195 @default.
- W2004019504 hasRelatedWork W626230106 @default.
- W2004019504 hasRelatedWork W99192079 @default.
- W2004019504 hasRelatedWork W2462936459 @default.
- W2004019504 isParatext "false" @default.
- W2004019504 isRetracted "false" @default.
- W2004019504 magId "2004019504" @default.
- W2004019504 workType "article" @default.