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 1511–1520 of 1718 papers

TitleStatusHype
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning—0
Diffusion Models for Offline Multi-agent Reinforcement Learning with Safety Constraints—0
Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning—0
Directly Attention Loss Adjusted Prioritized Experience Replay—0
Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning—0
Discrete-Time Mean Field Control with Environment States—0
Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning—0
Distributed Autonomous Swarm Formation for Dynamic Network Bridging—0
Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph—0
Distributed Deep Reinforcement Learning for Functional Split Control in Energy Harvesting Virtualized Small Cells—0
Show:102550
← PrevPage 152 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