Deep Reinforcement Learning for Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Medium Transition.
Ricardo B. GrandoJunior Costa de JesusVictor Augusto KichAlisson Henrique KollingNicolas P. BortoluzziPedro M. PinheiroArmando Alves NetoPaulo Lilles Jorge Drews JuniorPublished in: ICRA (2021)
Keyphrases
- underwater vehicles
- reinforcement learning
- fault identification
- transition model
- computer simulation
- aerial images
- mathematical models
- multi agent
- learning algorithm
- function approximation
- robotic control
- vehicle tracking
- temporal difference learning
- deep learning
- reinforcement learning algorithms
- model free
- hybrid learning
- optimal policy
- state space
- state transition
- action selection
- temporal difference
- learning classifier systems
- learning problems
- experimental data
- reinforcement learning methods
- multispectral
- dynamic programming
- learning process