Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning.
Yulai ZhaoZhuoran YangZhaoran WangJason D. LeePublished in: CoRR (2023)
Keyphrases
- global optimality
- multi agent reinforcement learning
- globally optimal
- global optimization
- discrete optimization
- optimal solution
- multi agent
- semidefinite
- global minimum
- multi agent systems
- optimization problems
- learning agents
- objective function
- convex functions
- theoretical guarantees
- stochastic games
- gradient field
- multi agent learning
- reinforcement learning
- combinatorial optimization
- evolutionary algorithm
- machine learning
- pairwise
- global solution