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 1351–1360 of 1718 papers

TitleStatusHype
Transferable and Distributed User Association Policies for 5G and Beyond Networks—0
Decentralized Q-Learning in Zero-sum Markov Games—0
Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning—0
Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment—0
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning—0
MARL with General Utilities via Decentralized Shadow Reward Actor-Critic—0
KnowSR: Knowledge Sharing among Homogeneous Agents in Multi-agent Reinforcement Learning—0
From Motor Control to Team Play in Simulated Humanoid Football—0
Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound—0
Dependent Multi-Task Learning with Causal Intervention for Image Captioning—0
Show:102550
← PrevPage 136 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