Autonomous Racing using a Hybrid Imitation-Reinforcement Learning Architecture.
Chinmay Vilas SamakTanmay Vilas SamakSivanathan KandhasamyPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- learning capabilities
- management system
- function approximation
- machine learning
- autonomous learning
- autonomous systems
- reinforcement learning algorithms
- state space
- learning algorithm
- cooperative
- markov decision processes
- learning process
- optimal control
- multi layer
- network architecture
- reinforcement learning methods
- real time
- dynamic programming
- hidden markov models
- temporal difference
- multi agent
- temporal difference learning