Zero-Shot Policy Transfer in Autonomous Racing: Reinforcement Learning vs Imitation Learning.
Nathaniel HamiltonPatrick MusauDiego Manzanas LopezTaylor T. JohnsonPublished in: ICAA (2022)
Keyphrases
- imitation learning
- reinforcement learning
- optimal policy
- transfer learning
- action selection
- markov decision process
- robotic systems
- partially observable
- reinforcement learning methods
- state space
- function approximators
- function approximation
- policy iteration
- reward function
- markov decision processes
- partially observable markov decision processes
- reinforcement learning algorithms
- action space
- learning capabilities
- control problems
- model free
- multi agent
- temporal difference
- machine learning
- infinite horizon
- average reward
- computer vision
- optimal control
- learning problems
- hidden state
- long run
- supervised learning
- learning algorithm