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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 1251–1260 of 1718 papers

Title	Date	Tasks	Status	Hype
Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search	Jun 8, 2021	Model OptimizationMulti-agent Reinforcement Learning	—Unverified	0
Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning	Jun 7, 2021	Multi-agent Reinforcement LearningOffline RL	CodeCode Available	1
Truthful Self-Play	Jun 6, 2021	Multi-agent Reinforcement LearningStarcraft	—Unverified	0
MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning	Jun 5, 2021	Atari GamesCPU	CodeCode Available	1
Decentralized Q-Learning in Zero-sum Markov Games	Jun 4, 2021	Multi-agent Reinforcement LearningQ-Learning	—Unverified	0
Transferable and Distributed User Association Policies for 5G and Beyond Networks	Jun 4, 2021	ManagementMulti-agent Reinforcement Learning	—Unverified	0
Neural Auto-Curricula	Jun 4, 2021	Multi-agent Reinforcement Learning	CodeCode Available	1
Celebrating Diversity in Shared Multi-Agent Reinforcement Learning	Jun 4, 2021	DiversityMulti-agent Reinforcement Learning	CodeCode Available	1
Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment	Jun 1, 2021	ManagementMulti-agent Reinforcement Learning	—Unverified	0
Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning	Jun 1, 2021	counterfactualMulti-agent Reinforcement Learning	—Unverified	0

Show:10 25 50

← PrevPage 126 of 172Next →

All datasets ParticleEnvs Cooperative Communication SMAC-Exp UAV Logistics

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	MATD3	final agent reward	-14	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DRIMA	Median Win Rate	15	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Fusion-Multi-Actor-Attention-Critic	Average Reward	39	—	Unverified