Multi-agent reinforcement learning via double averaging primal-dual optimization

Keyphrases

• Double Averaging 100%
• Primal-dual Optimization 100%
• Multi-agent Reinforcement Learning 100%
• Convex-concave Saddle Point Problems 66%
• Power Grid 33%
• Sensor Networks 33%
• Complex Interactions 33%
• Policy Evaluation 33%
• Optimization Algorithm 33%
• Reinforcement Learning 33%
• Minimization Problem 33%
• State Action 33%
• Primal-dual 33%
• Averaging Scheme 33%
• Swarm Robotics 33%
• Gradient Information 33%
• Geometric Rate 33%
• Bellman Error Minimization 33%
• Fast Finite-time 33%
• Decentralized Applications 33%
• Finite-time Convergence 33%

Computer Science

• Primal-Dual 100%
• Multi-Agent Reinforcement Learning 100%
• Reinforcement Learning 33%
• Algorithm Converges 33%
• Swarm Robotics 33%
• Minimization Problem 33%
• Optimization Algorithm 33%
• Sensor Network 33%

Mathematics

• Saddle Point 100%
• Minimization Problem 50%
• Power Grid 50%
• Finite Time 50%
• Observed State 50%