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 661–670 of 1718 papers

TitleStatusHype
A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory ManagementCode1
A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning—0
Multi-Agent Reinforcement Learning Guided by Signal Temporal Logic Specifications—0
iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement LearningCode1
Robustness Testing for Multi-Agent Reinforcement Learning: State Perturbations on Critical Agents—0
Progression Cognition Reinforcement Learning with Prioritized Experience for Multi-Vehicle PursuitCode1
Negotiated Reasoning: On Provably Addressing Relative Over-Generalization—0
Inductive Bias for Emergent Communication in a Continuous Setting—0
A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement LearningCode0
MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement LearningCode1
Show:102550
← PrevPage 67 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