Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning

Keyphrases

• Multi-agent Reinforcement Learning 100%
• Welfare Function 66%
• Neural Network Architecture 33%
• Maximin 33%
• Centralized Training 33%
• Solution Method 33%
• Fully Decentralized 33%
• Proportional Fairness 33%
• Social Welfare Function 33%
• Fair Optimization 33%
• Policy Gradient 33%
• Learning Settings 33%
• Gini Coefficient 33%
• Decentralized Execution 33%

Computer Science

• Multi-Agent Reinforcement Learning 100%
• Subnetwork 66%
• Neural Network Architecture 33%
• Solution Method 33%
• Proportional Fairness 33%