A RL-based Policy Optimization Method Guided by Adaptive Stability Certification.
Shengjie WangFengbo LanXiang ZhengYuxue CaoOluwatosin OseniHaotian XuYang GaoTao ZhangPublished in: CoRR (2023)
Keyphrases
- optimization method
- optimization algorithm
- optimization methods
- optimal policy
- genetic algorithm
- optimization process
- evolutionary algorithm
- simulated annealing
- differential evolution
- optimization procedure
- reinforcement learning
- global optimum
- particle swarm
- nonlinear optimization
- metaheuristic
- action selection
- nelder mead simplex
- markov decision process
- control policy
- state space
- optimization strategy
- multi agent
- multi objective
- actor critic
- learning algorithm
- hybrid algorithm
- adaptive control
- search space
- quasi newton
- function approximation
- em algorithm
- policy iteration
- policy search