Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387143971> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4387143971 abstract "Although multi-agent reinforcement learning (MARL) has made significant progress in dealing with complex tasks, the hypothesis that agents act simultaneously still limits the applicability of MARL in many real-world problems. In this work, we relax such hypothesis by proposing a single-leader multi-followers Stackelberg game model. In this model, the leader considers the policy of the followers, and the followers make the best response based on the leader's action. By combining the single-leader multi-followers Stackelberg game model with Q-learning, we propose a Q-learning algorithm based on the Stackelberg game. We test a series of games, including Lumberjack and Predator Prey, which are challenging for existing MARL algorithms. Experimental results show that our method achieves competitive advantages in terms of performance and convergence speed." @default.
- W4387143971 created "2023-09-29" @default.
- W4387143971 creator A5021471823 @default.
- W4387143971 creator A5041619246 @default.
- W4387143971 creator A5058983421 @default.
- W4387143971 date "2023-07-11" @default.
- W4387143971 modified "2023-10-18" @default.
- W4387143971 title "A Multi-Agent Q-Learning with Value Function Approximation Based on Single-leader Multi-followers Stackelberg Game" @default.
- W4387143971 cites W1542941925 @default.
- W4387143971 cites W2492629073 @default.
- W4387143971 cites W2997072274 @default.
- W4387143971 cites W2997502221 @default.
- W4387143971 cites W4312315130 @default.
- W4387143971 doi "https://doi.org/10.1109/cyber59472.2023.10256524" @default.
- W4387143971 hasPublicationYear "2023" @default.
- W4387143971 type Work @default.
- W4387143971 citedByCount "0" @default.
- W4387143971 crossrefType "proceedings-article" @default.
- W4387143971 hasAuthorship W4387143971A5021471823 @default.
- W4387143971 hasAuthorship W4387143971A5041619246 @default.
- W4387143971 hasAuthorship W4387143971A5058983421 @default.
- W4387143971 hasConcept C119857082 @default.
- W4387143971 hasConcept C126255220 @default.
- W4387143971 hasConcept C14036430 @default.
- W4387143971 hasConcept C144237770 @default.
- W4387143971 hasConcept C154945302 @default.
- W4387143971 hasConcept C162324750 @default.
- W4387143971 hasConcept C188116033 @default.
- W4387143971 hasConcept C199510392 @default.
- W4387143971 hasConcept C2776291640 @default.
- W4387143971 hasConcept C2777303404 @default.
- W4387143971 hasConcept C33923547 @default.
- W4387143971 hasConcept C41008148 @default.
- W4387143971 hasConcept C50522688 @default.
- W4387143971 hasConcept C78458016 @default.
- W4387143971 hasConcept C86803240 @default.
- W4387143971 hasConcept C97541855 @default.
- W4387143971 hasConceptScore W4387143971C119857082 @default.
- W4387143971 hasConceptScore W4387143971C126255220 @default.
- W4387143971 hasConceptScore W4387143971C14036430 @default.
- W4387143971 hasConceptScore W4387143971C144237770 @default.
- W4387143971 hasConceptScore W4387143971C154945302 @default.
- W4387143971 hasConceptScore W4387143971C162324750 @default.
- W4387143971 hasConceptScore W4387143971C188116033 @default.
- W4387143971 hasConceptScore W4387143971C199510392 @default.
- W4387143971 hasConceptScore W4387143971C2776291640 @default.
- W4387143971 hasConceptScore W4387143971C2777303404 @default.
- W4387143971 hasConceptScore W4387143971C33923547 @default.
- W4387143971 hasConceptScore W4387143971C41008148 @default.
- W4387143971 hasConceptScore W4387143971C50522688 @default.
- W4387143971 hasConceptScore W4387143971C78458016 @default.
- W4387143971 hasConceptScore W4387143971C86803240 @default.
- W4387143971 hasConceptScore W4387143971C97541855 @default.
- W4387143971 hasLocation W43871439711 @default.
- W4387143971 hasOpenAccess W4387143971 @default.
- W4387143971 hasPrimaryLocation W43871439711 @default.
- W4387143971 hasRelatedWork W1626977535 @default.
- W4387143971 hasRelatedWork W1973039793 @default.
- W4387143971 hasRelatedWork W2145363145 @default.
- W4387143971 hasRelatedWork W2171609577 @default.
- W4387143971 hasRelatedWork W2361707576 @default.
- W4387143971 hasRelatedWork W2703664903 @default.
- W4387143971 hasRelatedWork W2761465998 @default.
- W4387143971 hasRelatedWork W4206669594 @default.
- W4387143971 hasRelatedWork W4301204068 @default.
- W4387143971 hasRelatedWork W4378771262 @default.
- W4387143971 isParatext "false" @default.
- W4387143971 isRetracted "false" @default.
- W4387143971 workType "article" @default.