Sign in
A novel policy gradient algorithm with PSO-based parameter exploration for continuous control.
Tundong Liu
Liduan Li
Guifang Shao
Xiaomin Wu
Meng Huang
Published in:
Eng. Appl. Artif. Intell. (2020)
Keyphrases
</>
particle swarm optimization
computational complexity
learning algorithm
objective function
optimal solution
worst case
np hard
dynamic programming
optimization algorithm
optimal control
policy gradient
cost function
neural network
optimal policy
path planning
control strategies
average reward
actor critic