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 421–430 of 1718 papers

TitleStatusHype
Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning—0
Dialogue Management based on Multi-domain Corpus—0
DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization—0
Difference Rewards Policy Gradients—0
Differentiable Arbitrating in Zero-sum Markov Games—0
Differentially Private Reinforcement Learning with Self-Play—0
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning—0
Diffusion Models for Offline Multi-agent Reinforcement Learning with Safety Constraints—0
Calculus of Consent via MARL: Legitimating the Collaborative Governance Supplying Public Goods—0
Decentralized Policy Optimization—0
Show:102550
← PrevPage 43 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