Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386272798> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4386272798 abstract "Standard cooperative multi-agent reinforcement learning (MARL) methods aim to find the optimal team cooperative policy to complete a task. However there may exist multiple different ways of cooperating, which usually are very needed by domain experts. Therefore, identifying a set of significantly different policies can alleviate the task complexity for them. Unfortunately, there is a general lack of effective policy diversity approaches specifically designed for the multi-agent domain. In this work, we propose a method called Moment-Matching Policy Diversity to alleviate this problem. This method can generate different team policies to varying degrees by formalizing the difference between team policies as the difference in actions of selected agents in different policies. Theoretically, we show that our method is a simple way to implement a constrained optimization problem that regularizes the difference between two trajectory distributions by using the maximum mean discrepancy. The effectiveness of our approach is demonstrated on a challenging team-based shooter." @default.
- W4386272798 created "2023-08-31" @default.
- W4386272798 creator A5015880774 @default.
- W4386272798 creator A5027101473 @default.
- W4386272798 creator A5029152749 @default.
- W4386272798 date "2023-08-28" @default.
- W4386272798 modified "2023-09-30" @default.
- W4386272798 title "Policy Diversity for Cooperative Agents" @default.
- W4386272798 doi "https://doi.org/10.48550/arxiv.2308.14308" @default.
- W4386272798 hasPublicationYear "2023" @default.
- W4386272798 type Work @default.
- W4386272798 citedByCount "0" @default.
- W4386272798 crossrefType "posted-content" @default.
- W4386272798 hasAuthorship W4386272798A5015880774 @default.
- W4386272798 hasAuthorship W4386272798A5027101473 @default.
- W4386272798 hasAuthorship W4386272798A5029152749 @default.
- W4386272798 hasBestOaLocation W43862727981 @default.
- W4386272798 hasConcept C105795698 @default.
- W4386272798 hasConcept C119857082 @default.
- W4386272798 hasConcept C121332964 @default.
- W4386272798 hasConcept C126255220 @default.
- W4386272798 hasConcept C127413603 @default.
- W4386272798 hasConcept C1276947 @default.
- W4386272798 hasConcept C134306372 @default.
- W4386272798 hasConcept C13662910 @default.
- W4386272798 hasConcept C154945302 @default.
- W4386272798 hasConcept C165064840 @default.
- W4386272798 hasConcept C177264268 @default.
- W4386272798 hasConcept C17744445 @default.
- W4386272798 hasConcept C199360897 @default.
- W4386272798 hasConcept C199539241 @default.
- W4386272798 hasConcept C201995342 @default.
- W4386272798 hasConcept C2780451532 @default.
- W4386272798 hasConcept C2781316041 @default.
- W4386272798 hasConcept C33923547 @default.
- W4386272798 hasConcept C36503486 @default.
- W4386272798 hasConcept C41008148 @default.
- W4386272798 hasConcept C97541855 @default.
- W4386272798 hasConceptScore W4386272798C105795698 @default.
- W4386272798 hasConceptScore W4386272798C119857082 @default.
- W4386272798 hasConceptScore W4386272798C121332964 @default.
- W4386272798 hasConceptScore W4386272798C126255220 @default.
- W4386272798 hasConceptScore W4386272798C127413603 @default.
- W4386272798 hasConceptScore W4386272798C1276947 @default.
- W4386272798 hasConceptScore W4386272798C134306372 @default.
- W4386272798 hasConceptScore W4386272798C13662910 @default.
- W4386272798 hasConceptScore W4386272798C154945302 @default.
- W4386272798 hasConceptScore W4386272798C165064840 @default.
- W4386272798 hasConceptScore W4386272798C177264268 @default.
- W4386272798 hasConceptScore W4386272798C17744445 @default.
- W4386272798 hasConceptScore W4386272798C199360897 @default.
- W4386272798 hasConceptScore W4386272798C199539241 @default.
- W4386272798 hasConceptScore W4386272798C201995342 @default.
- W4386272798 hasConceptScore W4386272798C2780451532 @default.
- W4386272798 hasConceptScore W4386272798C2781316041 @default.
- W4386272798 hasConceptScore W4386272798C33923547 @default.
- W4386272798 hasConceptScore W4386272798C36503486 @default.
- W4386272798 hasConceptScore W4386272798C41008148 @default.
- W4386272798 hasConceptScore W4386272798C97541855 @default.
- W4386272798 hasLocation W43862727981 @default.
- W4386272798 hasOpenAccess W4386272798 @default.
- W4386272798 hasPrimaryLocation W43862727981 @default.
- W4386272798 hasRelatedWork W260766989 @default.
- W4386272798 hasRelatedWork W2959276766 @default.
- W4386272798 hasRelatedWork W2961085424 @default.
- W4386272798 hasRelatedWork W3020724165 @default.
- W4386272798 hasRelatedWork W3074294383 @default.
- W4386272798 hasRelatedWork W3139193008 @default.
- W4386272798 hasRelatedWork W4206669594 @default.
- W4386272798 hasRelatedWork W4295941380 @default.
- W4386272798 hasRelatedWork W4319083788 @default.
- W4386272798 hasRelatedWork W88370528 @default.
- W4386272798 isParatext "false" @default.
- W4386272798 isRetracted "false" @default.
- W4386272798 workType "article" @default.