Policy Gradient Adaptive Dynamic Programming for Model-Free Multi-Objective Optimal Control.
Hao ZhangYan LiZhuping WangYi DingHuaicheng YanPublished in: IEEE CAA J. Autom. Sinica (2024)
Keyphrases
- optimal control
- model free
- policy gradient
- dynamic programming
- reinforcement learning
- multi objective
- actor critic
- reinforcement learning algorithms
- policy iteration
- rl algorithms
- function approximation
- impedance control
- control problems
- average reward
- state space
- evolutionary algorithm
- infinite horizon
- temporal difference
- control law
- optimal policy
- adaptive control
- reinforcement learning methods
- approximate dynamic programming
- partially observable
- linear programming
- objective function
- learning algorithm
- genetic algorithm
- particle swarm optimization
- data mining
- learning problems
- markov decision processes
- control strategy
- average cost