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 821–830 of 1718 papers

TitleStatusHype
TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning ProblemsCode1
Learning to Control and Coordinate Mixed Traffic Through Robot Vehicles at Complex and Unsignalized IntersectionsCode1
SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learning—0
Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative ExplorationCode1
Multi-Agent Reinforcement Learning for Fast-Timescale Demand Response of Residential Loads—0
Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism—0
Self-Motivated Multi-Agent ExplorationCode0
Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on VideosCode0
Distributed Machine Learning for UAV Swarms: Computing, Sensing, and Semantics—0
Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning—0
Show:102550
← PrevPage 83 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