Optimal Combination of Imitation and Reinforcement Learning for Self-driving Cars.
Youssef FenjiroHouda BenbrahimPublished in: Rev. d'Intelligence Artif. (2019)
Keyphrases
- reinforcement learning
- optimal control
- dynamic programming
- state space
- learning algorithm
- optimal design
- function approximation
- markov decision processes
- data sets
- reinforcement learning algorithms
- control policy
- average reward
- np hard
- multi agent
- average cost
- policy search
- optimal kernel
- model free
- closed form
- optimal policy
- sufficient conditions
- worst case
- machine learning