Reinforcement Learning-Based Mapless Navigation with Fail-Safe Localisation.

Feiqiang Lin Ze Ji Changyun Wei Hanlin Niu

Published in: TAROS (2021)

Keyphrases

reinforcement learning
function approximation
reinforcement learning algorithms
model free
machine learning
indoor environments
optimal policy

outdoor environments
policy search
markov decision processes
dynamic programming
learning process
multi agent
learning algorithm

robotic control
e learning
genetic algorithm
action selection
temporal difference
real time
markov decision process

multi agent reinforcement learning
direct policy search
temporal difference learning
topological map
robot navigation
state space
data sets