Actor-Critic with variable time discretization via sustained actions.
Jakub LyskawaPawel WawrzynskiPublished in: CoRR (2023)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- neuro fuzzy
- policy gradient
- gradient method
- continuous variables
- approximate dynamic programming
- action selection
- optimal control
- average reward
- function approximation
- machine learning
- optimal policy
- partially observable
- situation calculus
- decision problems
- policy iteration
- naive bayes classifier
- reward function
- radial basis function