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 1611–1620 of 1718 papers

TitleStatusHype
Multiple Landmark Detection using Multi-Agent Reinforcement LearningCode0
Dealing with Non-Stationarity in Multi-Agent Deep Reinforcement Learning—0
Escaping the State of Nature: A Hobbesian Approach to Cooperation in Multi-agent Reinforcement Learning—0
Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning—0
Finding Friend and Foe in Multi-Agent GamesCode0
Options as responses: Grounding behavioural hierarchies in multi-agent RL—0
Learning Transferable Cooperative Behavior in Multi-Agent TeamsCode0
Attentional Policies for Cross-Context Multi-Agent Reinforcement Learning—0
AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning—0
PAC Guarantees for Cooperative Multi-Agent Reinforcement Learning with Restricted Communication—0
Show:102550
← PrevPage 162 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