A Novel Augmentative Backward Reward Function with Deep Reinforcement Learning for Autonomous UAV Navigation.
Manit ChansuparpKulsawasd JitkajornwanichPublished in: Appl. Artif. Intell. (2022)
Keyphrases
- reward function
- reinforcement learning
- unmanned aerial vehicles
- land vehicle
- reinforcement learning algorithms
- autonomous vehicles
- autonomous navigation
- path planning
- state space
- markov decision processes
- optimal policy
- partially observable
- inverse reinforcement learning
- policy search
- markov decision process
- dynamic environments
- hierarchical reinforcement learning
- function approximation
- multiple agents
- learning capabilities
- multi agent
- learning agent
- initially unknown
- model free
- learning algorithm
- state action
- transition model
- transition probabilities
- generative model
- optimal control
- higher order
- average reward
- temporal difference