Sign in
Velocity range-based reward shaping technique for effective map-less navigation with LiDAR sensor and deep reinforcement learning.
Hyeoksoo Lee
Jongpil Jeong
Published in:
Frontiers Neurorobotics (2023)
Keyphrases
</>
reinforcement learning
reward shaping
reinforcement learning algorithms
neural network
complex domains
multi agent
state space
intelligent agents
markov decision processes
model free
temporal difference