Model-Free Source Seeking by a Novel Single-Integrator with Attenuating Oscillations and Better Convergence Rate: Robotic Experiments.
Shivam BajpaiAhmed A. ElgoharySameh A. EisaPublished in: ECC (2024)
Keyphrases
- convergence rate
- model free
- policy iteration
- convergence speed
- step size
- reinforcement learning
- learning rate
- reinforcement learning algorithms
- function approximation
- temporal difference
- gradient method
- numerical stability
- markov decision processes
- robotic systems
- faster convergence rate
- machine learning
- optimal control
- mobile robot
- feature extraction