DoCRL: Double Critic Deep Reinforcement Learning for Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Medium Transition.
Ricardo B. GrandoJunior Costa de JesusVictor Augusto KichAlisson Henrique KollingMatheus G. MateusRodrigo da Silva GuerraPaulo L. J. Drews-JrPublished in: LARS/SBR/WRE (2023)
Keyphrases
- underwater vehicles
- reinforcement learning
- fault identification
- function approximation
- reinforcement learning algorithms
- actor critic
- transition model
- temporal difference
- computer simulation
- markov decision processes
- state space
- satellite images
- policy gradient
- mathematical models
- multi agent
- model free
- neuro fuzzy
- optimal policy
- dynamic programming
- deep learning
- vehicle tracking
- machine learning
- evaluation function
- artificial intelligence