Matches in SemOpenAlex for { <https://semopenalex.org/work/W331605669> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W331605669 abstract "In this paper, we address the issue of rational communication behavior among autonomous agents. We extend our previously reported cooperative hierarchical reinforcement learning (HRL) algorithm to include communication decision and propose a new multiagent HRL algorithm, called COM-Cooperative HRL. In this algorithm, at specific levels of the hierarchy, called cooperation levels, a group of subtasks, in which coordination among agents has significant effect on the performance of the overall task, are defined as cooperative subtasks. Coordination skills among agents are learned faster by sharing information at cooperation levels, rather than the level of primitive actions. We add a communication level to the hierarchical decomposition of the problem, below each cooperation level. A communication action has a certain cost and is used by each agent to obtain the actions selected by the cooperative subtasks of the other agents. Before making a decision at a cooperative subtask, agents decide if it is worthwhile to perform a communication action in order to acquire the actions chosen by the cooperative subtasks of the other agents. Using this algorithm, agents learn a policy to balance the amount of communication needed for proper coordination, and communication cost. We demonstrate the efficacy of the COM-Cooperative HRL algorithm as well as the relation between communication cost and the learned communication policy, using a multiagent taxi domain.1" @default.
- W331605669 created "2016-06-24" @default.
- W331605669 creator A5013843778 @default.
- W331605669 creator A5061960274 @default.
- W331605669 date "2004-01-01" @default.
- W331605669 modified "2023-10-10" @default.
- W331605669 title "Learning to Communicate and Act in Cooperative Multiagent Systems using Hierarchical Reinforcement Learning" @default.
- W331605669 cites W1484740474 @default.
- W331605669 cites W1488636191 @default.
- W331605669 cites W1536258751 @default.
- W331605669 cites W1574700590 @default.
- W331605669 cites W1590759229 @default.
- W331605669 cites W1641379095 @default.
- W331605669 cites W1982678075 @default.
- W331605669 cites W2109910161 @default.
- W331605669 cites W2114134981 @default.
- W331605669 cites W2118318536 @default.
- W331605669 cites W2120327309 @default.
- W331605669 cites W2121517924 @default.
- W331605669 cites W2147538364 @default.
- W331605669 cites W2161966858 @default.
- W331605669 cites W256201028 @default.
- W331605669 hasPublicationYear "2004" @default.
- W331605669 type Work @default.
- W331605669 sameAs 331605669 @default.
- W331605669 citedByCount "4" @default.
- W331605669 crossrefType "journal-article" @default.
- W331605669 hasAuthorship W331605669A5013843778 @default.
- W331605669 hasAuthorship W331605669A5061960274 @default.
- W331605669 hasConcept C120314980 @default.
- W331605669 hasConcept C121332964 @default.
- W331605669 hasConcept C124681953 @default.
- W331605669 hasConcept C127413603 @default.
- W331605669 hasConcept C154945302 @default.
- W331605669 hasConcept C162324750 @default.
- W331605669 hasConcept C18903297 @default.
- W331605669 hasConcept C201995342 @default.
- W331605669 hasConcept C2780451532 @default.
- W331605669 hasConcept C2780791683 @default.
- W331605669 hasConcept C31170391 @default.
- W331605669 hasConcept C34447519 @default.
- W331605669 hasConcept C41008148 @default.
- W331605669 hasConcept C41550386 @default.
- W331605669 hasConcept C62520636 @default.
- W331605669 hasConcept C86803240 @default.
- W331605669 hasConcept C97541855 @default.
- W331605669 hasConceptScore W331605669C120314980 @default.
- W331605669 hasConceptScore W331605669C121332964 @default.
- W331605669 hasConceptScore W331605669C124681953 @default.
- W331605669 hasConceptScore W331605669C127413603 @default.
- W331605669 hasConceptScore W331605669C154945302 @default.
- W331605669 hasConceptScore W331605669C162324750 @default.
- W331605669 hasConceptScore W331605669C18903297 @default.
- W331605669 hasConceptScore W331605669C201995342 @default.
- W331605669 hasConceptScore W331605669C2780451532 @default.
- W331605669 hasConceptScore W331605669C2780791683 @default.
- W331605669 hasConceptScore W331605669C31170391 @default.
- W331605669 hasConceptScore W331605669C34447519 @default.
- W331605669 hasConceptScore W331605669C41008148 @default.
- W331605669 hasConceptScore W331605669C41550386 @default.
- W331605669 hasConceptScore W331605669C62520636 @default.
- W331605669 hasConceptScore W331605669C86803240 @default.
- W331605669 hasConceptScore W331605669C97541855 @default.
- W331605669 hasLocation W3316056691 @default.
- W331605669 hasOpenAccess W331605669 @default.
- W331605669 hasPrimaryLocation W3316056691 @default.
- W331605669 hasRelatedWork W1227619798 @default.
- W331605669 hasRelatedWork W1500944602 @default.
- W331605669 hasRelatedWork W1516518151 @default.
- W331605669 hasRelatedWork W1536258751 @default.
- W331605669 hasRelatedWork W1537642095 @default.
- W331605669 hasRelatedWork W1543480674 @default.
- W331605669 hasRelatedWork W1586942805 @default.
- W331605669 hasRelatedWork W1801034623 @default.
- W331605669 hasRelatedWork W1974812331 @default.
- W331605669 hasRelatedWork W1978274720 @default.
- W331605669 hasRelatedWork W2025406794 @default.
- W331605669 hasRelatedWork W2048721916 @default.
- W331605669 hasRelatedWork W2088956500 @default.
- W331605669 hasRelatedWork W2102764452 @default.
- W331605669 hasRelatedWork W2110158409 @default.
- W331605669 hasRelatedWork W2114423199 @default.
- W331605669 hasRelatedWork W2222136216 @default.
- W331605669 hasRelatedWork W2383446267 @default.
- W331605669 hasRelatedWork W3143597629 @default.
- W331605669 hasRelatedWork W3162382249 @default.
- W331605669 isParatext "false" @default.
- W331605669 isRetracted "false" @default.
- W331605669 magId "331605669" @default.
- W331605669 workType "article" @default.