Localisation-Safe Reinforcement Learning for Mapless Navigation.
Feiqiang LinZe JiChangyun WeiRaphael GrechPublished in: ROBIO (2022)
Keyphrases
- reinforcement learning
- state space
- function approximation
- learning algorithm
- multi agent
- reinforcement learning algorithms
- dynamic programming
- optimal policy
- neural network
- temporal difference learning
- control policy
- obstacle avoidance
- action selection
- model free
- indoor environments
- optimal control
- learning problems
- markov decision processes
- supervised learning
- transfer learning
- robot navigation
- temporal difference
- mobile robot
- hidden markov models
- control problems
- autonomous vehicles
- navigation systems
- information systems
- real time
- multi agent reinforcement learning
- land vehicle