Design of Reward Functions for RL-based High-Speed Autonomous Driving.

Tanaka Kohsuke Shintomi Yuta Okuyama Yuichi Suzuki Taro

Published in: MCSoC (2022)

Keyphrases

high speed
reinforcement learning
reward function
markov decision processes
autonomous driving
optimal policy
optimal solution
state space
dynamical systems
reinforcement learning algorithms