Navigation Through Endoluminal Channels Using Q-Learning.
Oded MedinaLiora KleinburdNir ShvalbPublished in: CoRR (2023)
Keyphrases
- potential field
- reinforcement learning
- multi agent
- function approximation
- cooperative
- state space
- learning algorithm
- robot navigation
- stochastic approximation
- optimal policy
- model free
- navigation systems
- indoor environments
- temporal difference learning
- path planning
- data sets
- autonomous navigation
- obstacle avoidance
- multi robot
- dynamic environments
- autonomous vehicles
- mobile robot
- real time
- td learning