IADRL: Imitation Augmented Deep Reinforcement Learning Enabled UGV-UAV Coalition for Tasking in Complex Environments.
Jian ZhangZhitao YuShiwen MaoSenthilkumar C. G. PeriaswamyJustin PattonXue XiaPublished in: IEEE Access (2020)
Keyphrases
- complex environments
- reinforcement learning
- learning agents
- sequential decision tasks
- function approximation
- autonomous agents
- state space
- coalition formation
- cooperative
- reinforcement learning algorithms
- multi agent
- model free
- control algorithm
- imitation learning
- markov decision processes
- path planning
- optimal policy
- temporal difference
- learning algorithm
- unmanned aerial vehicles
- transfer learning
- machine learning
- vision based navigation
- dynamic programming
- robotic control
- multi agent systems
- learning problems
- deep learning
- learning process
- adaptive control
- neural network
- learning agent
- markov decision process
- reinforcement learning methods
- cognitive systems
- reward function
- dynamic environments