Improving Actor-Critic Reinforcement Learning via Hamiltonian Policy.
Duo XuFaramarz FekriPublished in: CoRR (2021)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- approximate dynamic programming
- temporal difference
- reinforcement learning algorithms
- optimal control
- gradient method
- policy iteration
- function approximation
- neuro fuzzy
- policy gradient methods
- optimal policy
- natural actor critic
- state space
- markov decision processes
- control problems
- model free
- rl algorithms
- transfer learning
- dynamic programming
- function approximators
- reinforcement learning problems
- learning algorithm
- reward function
- machine learning
- infinite horizon
- fixed point
- action space
- decision problems
- linear program
- multi agent