Practical Critic Gradient based Actor Critic for On-Policy Reinforcement Learning.
Swaminathan GurumurthyZachary ManchesterJ. Zico KolterPublished in: L4DC (2023)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- approximate dynamic programming
- reinforcement learning algorithms
- optimal control
- policy iteration
- model free
- function approximation
- neuro fuzzy
- gradient method
- policy gradient methods
- state space
- markov decision processes
- average reward
- machine learning
- dynamic programming
- optimal policy
- linear program
- evaluation function
- multi agent
- natural actor critic
- temporal difference learning
- fixed point
- learning algorithm
- reinforcement learning problems
- convergence rate
- action selection
- linear programming
- supervised learning
- function approximators
- reinforcement learning methods