Multi-Skill Policy Transfer by Option-based Deep Reinforcement Learning for Autonomous Driving.
Bo WeiJianxin ZhaoYinuo ZhaoFeng TianPublished in: BIGCOM (2023)
Keyphrases
- autonomous driving
- reinforcement learning
- optimal policy
- grand challenge
- policy search
- transfer learning
- markov decision process
- action selection
- state space
- action space
- markov decision processes
- vision algorithms
- reward function
- control policy
- function approximation
- stereo vision
- machine learning
- function approximators
- policy gradient
- long run
- temporal difference
- infinite horizon
- optimal control
- object recognition
- multi agent
- three dimensional
- learning algorithm