SOTAVerified

Multi-agent Reinforcement Learning

The target of Multi-agent Reinforcement Learning is to solve complex problems by integrating multiple agents that focus on different sub-tasks. In general, there are two types of multi-agent systems: independent and cooperative systems.

Source: Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 881–890 of 1718 papers

TitleStatusHype
ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization—0
Combating Uncertainties in Wind and Distributed PV Energy Sources Using Integrated Reinforcement Learning and Time-Series Forecasting—0
Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control—0
Common Information based Approximate State Representations in Multi-Agent Reinforcement Learning—0
Communication-Aware Reinforcement Learning for Cooperative Adaptive Cruise Control—0
Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games—0
Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control—0
Communication-Efficient Policy Gradient Methods for Distributed Reinforcement Learning—0
Communication-Efficient MARL for Platoon Stability and Energy-efficiency Co-optimization in Cooperative Adaptive Cruise Control of CAVs—0
Communication in Multi-Agent Reinforcement Learning: Intention Sharing—0
Show:102550
← PrevPage 89 of 172Next →
All datasetsParticleEnvs Cooperative CommunicationSMAC-ExpUAV Logistics

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MATD3final agent reward-14—Unverified
#ModelMetricClaimedVerifiedStatus
1DRIMAMedian Win Rate15—Unverified
#ModelMetricClaimedVerifiedStatus
1Fusion-Multi-Actor-Attention-CriticAverage Reward39—Unverified