Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight.
Jiaxu XingAngel RomeroLeonard BauersfeldDavide ScaramuzzaPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- state space
- real time
- reinforcement learning algorithms
- multi agent
- human computer interaction
- flight data
- imitation learning
- markov decision processes
- information extraction
- machine learning
- vision system
- learning algorithm
- supervised learning
- temporal difference
- model free
- civil aviation
- project management
- transfer learning
- supply chain management
- augmented reality
- optimal policy
- reward function
- crew scheduling
- driver assistance systems
- optimal control
- learning process
- weakly supervised
- case study
- markov decision process
- reinforcement learning methods
- software development
- information retrieval
- development process
- dynamic programming