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 531–540 of 1718 papers

TitleStatusHype
Decentralized Adaptive Formation via Consensus-Oriented Multi-Agent Communication—0
A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem—0
Dealing with Non-Stationarity in MARL via Trust-Region Decomposition—0
Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning—0
B3C: A Minimalist Approach to Offline Multi-Agent Reinforcement Learning—0
Experience Augmentation: Boosting and Accelerating Off-Policy Multi-Agent Reinforcement Learning—0
Group-Agent Reinforcement Learning—0
DCMAC: Demand-aware Customized Multi-Agent Communication via Upper Bound Training—0
DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning—0
A Variational Approach to Mutual Information-Based Coordination for Multi-Agent Reinforcement Learning—0
Show:102550
← PrevPage 54 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