Improving Actor-Critic Reinforcement Learning via Hamiltonian Monte Carlo Method.
Duo XuFaramarz FekriPublished in: IEEE Trans. Artif. Intell. (2023)
Keyphrases
- actor critic
- reinforcement learning
- monte carlo method
- markov chain
- temporal difference
- monte carlo
- policy gradient
- reinforcement learning algorithms
- approximate dynamic programming
- optimal control
- state space
- neuro fuzzy
- function approximation
- gradient method
- policy iteration
- average reward
- genetic algorithm
- posterior distribution
- learning algorithm
- finite state
- optimal policy
- model free
- wavelet transform
- bayesian networks
- multi agent
- artificial neural networks
- function approximators
- markov decision processes
- markov random field
- action selection
- transfer learning