Parallelized and randomized adversarial imitation learning for safety-critical self-driving vehicles.
Won Joon YunMyungjae ShinSoyi JungSean S.-C. KwonJoongheon KimPublished in: J. Commun. Networks (2022)
Keyphrases
- safety critical
- imitation learning
- road traffic
- fault tolerant
- formal methods
- embedded systems
- reinforcement learning
- robotic systems
- agent architecture
- maximum margin
- real time
- humanoid robot
- support systems
- multi agent
- low cost
- adaptive systems
- maximum likelihood
- decision support system
- decision makers
- hyperplane
- active learning
- cooperative