FWA-RL: Fireworks Algorithm with Policy Gradient for Reinforcement Learning.
Maiyue ChenYing TanPublished in: CEC (2023)
Keyphrases
- reinforcement learning
- policy gradient
- actor critic
- learning algorithm
- dynamic programming
- temporal difference learning
- neural network
- gradient method
- path planning
- model free reinforcement learning
- policy iteration
- markov decision process
- single agent
- path finding
- function approximation
- learning problems
- monte carlo
- simulated annealing
- np hard
- cost function
- computational complexity