Generation of Geodesics with Actor-Critic Reinforcement Learning to Predict Midpoints.
Kazumi KasauraPublished in: CoRR (2024)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- optimal control
- function approximation
- neuro fuzzy
- approximate dynamic programming
- gradient method
- policy iteration
- state space
- markov decision processes
- average reward
- model free
- temporal difference learning
- natural actor critic
- learning algorithm
- learning problems
- multi agent
- machine learning
- partially observable
- step size
- dynamical systems
- rl algorithms
- monte carlo
- dynamic programming
- policy gradient methods