Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement.
Tianyu ShiDong ChenKaian ChenZhaojian LiPublished in: CoRR (2021)
Keyphrases
- autonomous driving
- reinforcement learning
- grand challenge
- active exploration
- exploration strategy
- action selection
- stereo vision
- real time
- exploration exploitation tradeoff
- function approximation
- vision algorithms
- multi agent
- image processing
- markov decision processes
- autonomous learning
- learning algorithm
- state space
- cellular automata
- image sequences