Multi-Agent First Order Constrained Optimization in Policy Space.
Youpeng ZhaoYaodong YangZhenbo LuWengang ZhouHouqiang LiPublished in: NeurIPS (2023)
Keyphrases
- constrained optimization
- multi agent
- constrained optimization problems
- objective function
- unconstrained optimization
- augmented lagrangian
- constraint handling
- penalty function
- penalty functions
- lagrange multipliers
- multi agent systems
- inequality constraints
- interval analysis
- iterative methods
- reinforcement learning
- cost function
- lagrange multiplier method