Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316829835> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4316829835 abstract "Coordination is one of the most difficult aspects of multi-agent reinforcement learning (MARL). One reason is that agents normally choose their actions independently of one another. In order to see coordination strategies emerging from the combination of independent policies, the recent research has focused on the use of a centralized function (CF) that learns each agent's contribution to the team reward. However, the structure in which the environment is presented to the agents and to the CF is typically overlooked. We have observed that the features used to describe the coordination problem can be represented as vertex features of a latent graph structure. Here, we present TransfQMix, a new approach that uses transformers to leverage this latent structure and learn better coordination policies. Our transformer agents perform a graph reasoning over the state of the observable entities. Our transformer Q-mixer learns a monotonic mixing-function from a larger graph that includes the internal and external states of the agents. TransfQMix is designed to be entirely transferable, meaning that same parameters can be used to control and train larger or smaller teams of agents. This enables to deploy promising approaches to save training time and derive general policies in MARL, such as transfer learning, zero-shot transfer, and curriculum learning. We report TransfQMix's performances in the Spread and StarCraft II environments. In both settings, it outperforms state-of-the-art Q-Learning models, and it demonstrates effectiveness in solving problems that other methods can not solve." @default.
- W4316829835 created "2023-01-17" @default.
- W4316829835 creator A5008938807 @default.
- W4316829835 creator A5026842131 @default.
- W4316829835 creator A5052414260 @default.
- W4316829835 date "2023-01-12" @default.
- W4316829835 modified "2023-10-16" @default.
- W4316829835 title "TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems" @default.
- W4316829835 doi "https://doi.org/10.48550/arxiv.2301.05334" @default.
- W4316829835 hasPublicationYear "2023" @default.
- W4316829835 type Work @default.
- W4316829835 citedByCount "0" @default.
- W4316829835 crossrefType "posted-content" @default.
- W4316829835 hasAuthorship W4316829835A5008938807 @default.
- W4316829835 hasAuthorship W4316829835A5026842131 @default.
- W4316829835 hasAuthorship W4316829835A5052414260 @default.
- W4316829835 hasBestOaLocation W43168298351 @default.
- W4316829835 hasConcept C119599485 @default.
- W4316829835 hasConcept C119857082 @default.
- W4316829835 hasConcept C127413603 @default.
- W4316829835 hasConcept C132525143 @default.
- W4316829835 hasConcept C153083717 @default.
- W4316829835 hasConcept C154945302 @default.
- W4316829835 hasConcept C165801399 @default.
- W4316829835 hasConcept C41008148 @default.
- W4316829835 hasConcept C66322947 @default.
- W4316829835 hasConcept C80444323 @default.
- W4316829835 hasConcept C97541855 @default.
- W4316829835 hasConceptScore W4316829835C119599485 @default.
- W4316829835 hasConceptScore W4316829835C119857082 @default.
- W4316829835 hasConceptScore W4316829835C127413603 @default.
- W4316829835 hasConceptScore W4316829835C132525143 @default.
- W4316829835 hasConceptScore W4316829835C153083717 @default.
- W4316829835 hasConceptScore W4316829835C154945302 @default.
- W4316829835 hasConceptScore W4316829835C165801399 @default.
- W4316829835 hasConceptScore W4316829835C41008148 @default.
- W4316829835 hasConceptScore W4316829835C66322947 @default.
- W4316829835 hasConceptScore W4316829835C80444323 @default.
- W4316829835 hasConceptScore W4316829835C97541855 @default.
- W4316829835 hasLocation W43168298351 @default.
- W4316829835 hasOpenAccess W4316829835 @default.
- W4316829835 hasPrimaryLocation W43168298351 @default.
- W4316829835 hasRelatedWork W2904145923 @default.
- W4316829835 hasRelatedWork W2971239080 @default.
- W4316829835 hasRelatedWork W3022038857 @default.
- W4316829835 hasRelatedWork W3203000071 @default.
- W4316829835 hasRelatedWork W3210855527 @default.
- W4316829835 hasRelatedWork W4210912933 @default.
- W4316829835 hasRelatedWork W4283701713 @default.
- W4316829835 hasRelatedWork W4293575545 @default.
- W4316829835 hasRelatedWork W4307308173 @default.
- W4316829835 hasRelatedWork W4315778373 @default.
- W4316829835 isParatext "false" @default.
- W4316829835 isRetracted "false" @default.
- W4316829835 workType "article" @default.