FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312862010> ?p ?o ?g. }

• W4312862010 abstract "Many real-world applications can be formulated as multi-agent cooperation problems, such as network packet routing and coordination of autonomous vehicles. The emergence of deep reinforcement learning (DRL) provides a promising approach for multi-agent cooperation through the interaction of the agents and environments. However, traditional DRL solutions suffer from the high dimensions of multiple agents with continuous action space during policy search. Besides, the dynamicity of agents’ policies makes the training non-stationary. To tackle the issues, we propose a hierarchical reinforcement learning approach with high-level decision-making and low-level individual control for efficient policy search. In particular, the cooperation of multiple agents can be learned in high-level discrete action space efficiently. At the same time, the low-level individual control can be reduced to single-agent reinforcement learning. In addition to hierarchical reinforcement learning, we propose an opponent modeling network to model other agents’ policies during the learning process. In contrast to end-to-end DRL approaches, our approach reduces the learning complexity by decomposing the overall task into sub-tasks in a hierarchical way. To evaluate the efficiency of our approach, we conduct a real-world case study in the cooperative lane change scenario. Both simulation and real-world experiments show the superiority of our approach in the collision rate and convergence speed." @default.
• W4312862010 created "2023-01-05" @default.
• W4312862010 creator A5013565764 @default.
• W4312862010 creator A5039357179 @default.
• W4312862010 creator A5054296164 @default.
• W4312862010 creator A5055870001 @default.
• W4312862010 creator A5069419555 @default.
• W4312862010 date "2022-07-01" @default.
• W4312862010 modified "2023-09-26" @default.
• W4312862010 title "Hierarchical Reinforcement Learning with Opponent Modeling for Distributed Multi-agent Cooperation" @default.
• W4312862010 cites W1542941925 @default.
• W4312862010 cites W2099618002 @default.
• W4312862010 cites W2109910161 @default.
• W4312862010 cites W2121517924 @default.
• W4312862010 cites W2145339207 @default.
• W4312862010 cites W2167340365 @default.
• W4312862010 cites W2169977622 @default.
• W4312862010 cites W2180338159 @default.
• W4312862010 cites W2340259263 @default.
• W4312862010 cites W2524687611 @default.
• W4312862010 cites W2617547828 @default.
• W4312862010 cites W2940740707 @default.
• W4312862010 cites W2974078846 @default.
• W4312862010 cites W2981038142 @default.
• W4312862010 cites W3007080643 @default.
• W4312862010 cites W3056510116 @default.
• W4312862010 cites W3092786062 @default.
• W4312862010 cites W3128835378 @default.
• W4312862010 cites W3168892396 @default.
• W4312862010 doi "https://doi.org/10.1109/icdcs54860.2022.00090" @default.
• W4312862010 hasPublicationYear "2022" @default.
• W4312862010 type Work @default.
• W4312862010 citedByCount "1" @default.
• W4312862010 countsByYear W43128620102023 @default.
• W4312862010 crossrefType "proceedings-article" @default.
• W4312862010 hasAuthorship W4312862010A5013565764 @default.
• W4312862010 hasAuthorship W4312862010A5039357179 @default.
• W4312862010 hasAuthorship W4312862010A5054296164 @default.
• W4312862010 hasAuthorship W4312862010A5055870001 @default.
• W4312862010 hasAuthorship W4312862010A5069419555 @default.
• W4312862010 hasBestOaLocation W43128620102 @default.
• W4312862010 hasConcept C111919701 @default.
• W4312862010 hasConcept C119857082 @default.
• W4312862010 hasConcept C120314980 @default.
• W4312862010 hasConcept C121332964 @default.
• W4312862010 hasConcept C127413603 @default.
• W4312862010 hasConcept C13687954 @default.
• W4312862010 hasConcept C154945302 @default.
• W4312862010 hasConcept C158379750 @default.
• W4312862010 hasConcept C162324750 @default.
• W4312862010 hasConcept C201995342 @default.
• W4312862010 hasConcept C2777303404 @default.
• W4312862010 hasConcept C2780451532 @default.
• W4312862010 hasConcept C2780791683 @default.
• W4312862010 hasConcept C31258907 @default.
• W4312862010 hasConcept C38652104 @default.
• W4312862010 hasConcept C41008148 @default.
• W4312862010 hasConcept C41065033 @default.
• W4312862010 hasConcept C50522688 @default.
• W4312862010 hasConcept C62520636 @default.
• W4312862010 hasConcept C74072328 @default.
• W4312862010 hasConcept C97541855 @default.
• W4312862010 hasConcept C98045186 @default.
• W4312862010 hasConceptScore W4312862010C111919701 @default.
• W4312862010 hasConceptScore W4312862010C119857082 @default.
• W4312862010 hasConceptScore W4312862010C120314980 @default.
• W4312862010 hasConceptScore W4312862010C121332964 @default.
• W4312862010 hasConceptScore W4312862010C127413603 @default.
• W4312862010 hasConceptScore W4312862010C13687954 @default.
• W4312862010 hasConceptScore W4312862010C154945302 @default.
• W4312862010 hasConceptScore W4312862010C158379750 @default.
• W4312862010 hasConceptScore W4312862010C162324750 @default.
• W4312862010 hasConceptScore W4312862010C201995342 @default.
• W4312862010 hasConceptScore W4312862010C2777303404 @default.
• W4312862010 hasConceptScore W4312862010C2780451532 @default.
• W4312862010 hasConceptScore W4312862010C2780791683 @default.
• W4312862010 hasConceptScore W4312862010C31258907 @default.
• W4312862010 hasConceptScore W4312862010C38652104 @default.
• W4312862010 hasConceptScore W4312862010C41008148 @default.
• W4312862010 hasConceptScore W4312862010C41065033 @default.
• W4312862010 hasConceptScore W4312862010C50522688 @default.
• W4312862010 hasConceptScore W4312862010C62520636 @default.
• W4312862010 hasConceptScore W4312862010C74072328 @default.
• W4312862010 hasConceptScore W4312862010C97541855 @default.
• W4312862010 hasConceptScore W4312862010C98045186 @default.
• W4312862010 hasLocation W43128620101 @default.
• W4312862010 hasLocation W43128620102 @default.
• W4312862010 hasOpenAccess W4312862010 @default.
• W4312862010 hasPrimaryLocation W43128620101 @default.
• W4312862010 hasRelatedWork W2018749324 @default.
• W4312862010 hasRelatedWork W2316755582 @default.
• W4312862010 hasRelatedWork W2401692973 @default.
• W4312862010 hasRelatedWork W2416943787 @default.
• W4312862010 hasRelatedWork W2510455077 @default.
• W4312862010 hasRelatedWork W2979338733 @default.
• W4312862010 hasRelatedWork W2990027495 @default.
• W4312862010 hasRelatedWork W3022038857 @default.
• W4312862010 hasRelatedWork W4226227954 @default.
• W4312862010 hasRelatedWork W4288044926 @default.
• W4312862010 isParatext "false" @default.

• next