Matches in SemOpenAlex for { <https://semopenalex.org/work/W2114014700> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W2114014700 abstract "Large-scale agent-based systems are required to self-optimize towards multiple, potentially conflicting, policies of varying spatial and temporal scope. As a result, not all agents may be implementing all policies at all times, resulting in agent heterogeneity. As agents share their operating environment, significant dependencies can arise between agents and therefore between policy implementations. To address self-optimization in the presence of agent heterogeneity, policy dependency and the lack of global knowledge that is inherent in large-scale decentralized environments, we propose Distributed W-Learning (DWL). DWL is a reinforcement learning (RL)-based algorithm for collaborative agent-based self-optimization towards multiple policies, which relies only on local interactions and learning. We have evaluated the DWL algorithm in a simulation of a self-organizing urban traffic control (UTC) system and show that using DWL can improve the performance of multiple policies deployed simultaneously, even over corresponding single-policy deployments. For example, in UTC, optimizing simultaneously for cars and public transport vehicles reduces the waiting times of cars to 78% of their waiting times in the best-performing single-policy deployment that optimizes for cars only, while also outperforming the widely-deployed round-robin and saturation balancing traffic controllers that we used as baselines." @default.
- W2114014700 created "2016-06-24" @default.
- W2114014700 creator A5046960870 @default.
- W2114014700 creator A5059738292 @default.
- W2114014700 date "2009-09-01" @default.
- W2114014700 modified "2023-10-10" @default.
- W2114014700 title "Distributed W-Learning: Multi-Policy Optimization in Self-Organizing Systems" @default.
- W2114014700 cites W1557517019 @default.
- W2114014700 cites W1641379095 @default.
- W2114014700 cites W1968797214 @default.
- W2114014700 cites W1977712932 @default.
- W2114014700 cites W1984523211 @default.
- W2114014700 cites W2007716013 @default.
- W2114014700 cites W2023790196 @default.
- W2114014700 cites W2064916553 @default.
- W2114014700 cites W2073105339 @default.
- W2114014700 cites W2107544712 @default.
- W2114014700 cites W2113962893 @default.
- W2114014700 cites W2124657875 @default.
- W2114014700 cites W2130126738 @default.
- W2114014700 cites W2134698488 @default.
- W2114014700 cites W2156705373 @default.
- W2114014700 cites W4240076062 @default.
- W2114014700 doi "https://doi.org/10.1109/saso.2009.23" @default.
- W2114014700 hasPublicationYear "2009" @default.
- W2114014700 type Work @default.
- W2114014700 sameAs 2114014700 @default.
- W2114014700 citedByCount "28" @default.
- W2114014700 countsByYear W21140147002012 @default.
- W2114014700 countsByYear W21140147002013 @default.
- W2114014700 countsByYear W21140147002014 @default.
- W2114014700 countsByYear W21140147002015 @default.
- W2114014700 countsByYear W21140147002016 @default.
- W2114014700 countsByYear W21140147002017 @default.
- W2114014700 countsByYear W21140147002018 @default.
- W2114014700 countsByYear W21140147002019 @default.
- W2114014700 countsByYear W21140147002020 @default.
- W2114014700 countsByYear W21140147002021 @default.
- W2114014700 countsByYear W21140147002022 @default.
- W2114014700 crossrefType "proceedings-article" @default.
- W2114014700 hasAuthorship W2114014700A5046960870 @default.
- W2114014700 hasAuthorship W2114014700A5059738292 @default.
- W2114014700 hasBestOaLocation W21140147002 @default.
- W2114014700 hasConcept C105339364 @default.
- W2114014700 hasConcept C111919701 @default.
- W2114014700 hasConcept C120314980 @default.
- W2114014700 hasConcept C154945302 @default.
- W2114014700 hasConcept C199360897 @default.
- W2114014700 hasConcept C26713055 @default.
- W2114014700 hasConcept C2778012447 @default.
- W2114014700 hasConcept C41008148 @default.
- W2114014700 hasConcept C41550386 @default.
- W2114014700 hasConcept C97541855 @default.
- W2114014700 hasConceptScore W2114014700C105339364 @default.
- W2114014700 hasConceptScore W2114014700C111919701 @default.
- W2114014700 hasConceptScore W2114014700C120314980 @default.
- W2114014700 hasConceptScore W2114014700C154945302 @default.
- W2114014700 hasConceptScore W2114014700C199360897 @default.
- W2114014700 hasConceptScore W2114014700C26713055 @default.
- W2114014700 hasConceptScore W2114014700C2778012447 @default.
- W2114014700 hasConceptScore W2114014700C41008148 @default.
- W2114014700 hasConceptScore W2114014700C41550386 @default.
- W2114014700 hasConceptScore W2114014700C97541855 @default.
- W2114014700 hasLocation W21140147001 @default.
- W2114014700 hasLocation W21140147002 @default.
- W2114014700 hasLocation W21140147003 @default.
- W2114014700 hasOpenAccess W2114014700 @default.
- W2114014700 hasPrimaryLocation W21140147001 @default.
- W2114014700 hasRelatedWork W178231042 @default.
- W2114014700 hasRelatedWork W2360028903 @default.
- W2114014700 hasRelatedWork W2366083136 @default.
- W2114014700 hasRelatedWork W2566006169 @default.
- W2114014700 hasRelatedWork W2770234245 @default.
- W2114014700 hasRelatedWork W2987774938 @default.
- W2114014700 hasRelatedWork W4229499248 @default.
- W2114014700 hasRelatedWork W4280543773 @default.
- W2114014700 hasRelatedWork W4378874356 @default.
- W2114014700 hasRelatedWork W632915154 @default.
- W2114014700 isParatext "false" @default.
- W2114014700 isRetracted "false" @default.
- W2114014700 magId "2114014700" @default.
- W2114014700 workType "article" @default.