Critic Only Policy Iteration-based Zero-sum Neuro-optimal Control of Modular and Reconfigurable Robots with uncertain disturbance via Adaptive Dynamic Programming.
Tianjiao AnJingchen ChenXinye ZhuYuanchun LiKeping LiuBo DongPublished in: ICACI (2020)
Keyphrases
- optimal control
- actor critic
- dynamic programming
- policy iteration
- infinite horizon
- markov decision processes
- control problems
- stochastic games
- approximate dynamic programming
- reinforcement learning
- policy gradient
- optimal policy
- average reward
- state space
- control strategy
- control law
- decision making
- artificial neural networks
- multistage
- neural network
- policy iteration algorithm
- linear programming
- nash equilibria
- optimal solution
- model free
- finite state
- neuro fuzzy
- graphical models
- policy evaluation
- learning algorithm
- real time