Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313679571> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4313679571 abstract "In cooperative multi-agent reinforcement learning (CMARL), it is critical for agents to achieve a balance between self-exploration and team collaboration. However, agents can hardly accomplish the team task without coordination and they would be trapped in a local optimum where easy cooperation is accessed without enough individual exploration. Recent works mainly concentrate on agents' coordinated exploration, which brings about the exponentially grown exploration of the state space. To address this issue, we propose Self-Motivated Multi-Agent Exploration (SMMAE), which aims to achieve success in team tasks by adaptively finding a trade-off between self-exploration and team cooperation. In SMMAE, we train an independent exploration policy for each agent to maximize their own visited state space. Each agent learns an adjustable exploration probability based on the stability of the joint team policy. The experiments on highly cooperative tasks in StarCraft II micromanagement benchmark (SMAC) demonstrate that SMMAE can explore task-related states more efficiently, accomplish coordinated behaviours and boost the learning performance." @default.
- W4313679571 created "2023-01-08" @default.
- W4313679571 creator A5017781290 @default.
- W4313679571 creator A5024197542 @default.
- W4313679571 creator A5046214153 @default.
- W4313679571 creator A5073912249 @default.
- W4313679571 creator A5088385429 @default.
- W4313679571 date "2023-01-05" @default.
- W4313679571 modified "2023-10-05" @default.
- W4313679571 title "Self-Motivated Multi-Agent Exploration" @default.
- W4313679571 doi "https://doi.org/10.48550/arxiv.2301.02083" @default.
- W4313679571 hasPublicationYear "2023" @default.
- W4313679571 type Work @default.
- W4313679571 citedByCount "0" @default.
- W4313679571 crossrefType "posted-content" @default.
- W4313679571 hasAuthorship W4313679571A5017781290 @default.
- W4313679571 hasAuthorship W4313679571A5024197542 @default.
- W4313679571 hasAuthorship W4313679571A5046214153 @default.
- W4313679571 hasAuthorship W4313679571A5073912249 @default.
- W4313679571 hasAuthorship W4313679571A5088385429 @default.
- W4313679571 hasBestOaLocation W43136795711 @default.
- W4313679571 hasConcept C105795698 @default.
- W4313679571 hasConcept C111919701 @default.
- W4313679571 hasConcept C112972136 @default.
- W4313679571 hasConcept C11413529 @default.
- W4313679571 hasConcept C119857082 @default.
- W4313679571 hasConcept C127413603 @default.
- W4313679571 hasConcept C13280743 @default.
- W4313679571 hasConcept C154945302 @default.
- W4313679571 hasConcept C185798385 @default.
- W4313679571 hasConcept C201995342 @default.
- W4313679571 hasConcept C205649164 @default.
- W4313679571 hasConcept C2778572836 @default.
- W4313679571 hasConcept C2780451532 @default.
- W4313679571 hasConcept C33923547 @default.
- W4313679571 hasConcept C41008148 @default.
- W4313679571 hasConcept C48103436 @default.
- W4313679571 hasConcept C72434380 @default.
- W4313679571 hasConcept C97541855 @default.
- W4313679571 hasConceptScore W4313679571C105795698 @default.
- W4313679571 hasConceptScore W4313679571C111919701 @default.
- W4313679571 hasConceptScore W4313679571C112972136 @default.
- W4313679571 hasConceptScore W4313679571C11413529 @default.
- W4313679571 hasConceptScore W4313679571C119857082 @default.
- W4313679571 hasConceptScore W4313679571C127413603 @default.
- W4313679571 hasConceptScore W4313679571C13280743 @default.
- W4313679571 hasConceptScore W4313679571C154945302 @default.
- W4313679571 hasConceptScore W4313679571C185798385 @default.
- W4313679571 hasConceptScore W4313679571C201995342 @default.
- W4313679571 hasConceptScore W4313679571C205649164 @default.
- W4313679571 hasConceptScore W4313679571C2778572836 @default.
- W4313679571 hasConceptScore W4313679571C2780451532 @default.
- W4313679571 hasConceptScore W4313679571C33923547 @default.
- W4313679571 hasConceptScore W4313679571C41008148 @default.
- W4313679571 hasConceptScore W4313679571C48103436 @default.
- W4313679571 hasConceptScore W4313679571C72434380 @default.
- W4313679571 hasConceptScore W4313679571C97541855 @default.
- W4313679571 hasLocation W43136795711 @default.
- W4313679571 hasOpenAccess W4313679571 @default.
- W4313679571 hasPrimaryLocation W43136795711 @default.
- W4313679571 hasRelatedWork W1544566217 @default.
- W4313679571 hasRelatedWork W1997939726 @default.
- W4313679571 hasRelatedWork W2618318883 @default.
- W4313679571 hasRelatedWork W2729602312 @default.
- W4313679571 hasRelatedWork W2952905979 @default.
- W4313679571 hasRelatedWork W3090436287 @default.
- W4313679571 hasRelatedWork W3103643887 @default.
- W4313679571 hasRelatedWork W3173185086 @default.
- W4313679571 hasRelatedWork W4287647350 @default.
- W4313679571 hasRelatedWork W4294555834 @default.
- W4313679571 isParatext "false" @default.
- W4313679571 isRetracted "false" @default.
- W4313679571 workType "article" @default.