Feedback Linearization of Car Dynamics for Racing via Reinforcement Learning.
Michael EstradaSida LiXiangyu CaiPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- car racing
- function approximation
- dynamic model
- state space
- reinforcement learning algorithms
- temporal difference learning
- optimal policy
- learning algorithm
- multi agent
- multi agent reinforcement learning
- learning agents
- user feedback
- machine learning
- learning problems
- dynamical systems
- model free
- action selection
- temporal difference
- transfer learning
- initial conditions
- relevance feedback
- search space
- reinforcement learning methods
- search engine
- robotic control
- information retrieval