Prescribed intelligent elliptical pursuing by UAVs: A reinforcement learning policy.
Yi XiaXingling ShaoTianyun DingJun LiuPublished in: Expert Syst. Appl. (2024)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- reward function
- reinforcement learning algorithms
- state space
- partially observable environments
- reinforcement learning problems
- learning capabilities
- control policies
- markov decision processes
- markov decision problems
- intelligent systems
- partially observable
- unmanned aerial vehicles
- policy gradient
- function approximation
- policy evaluation
- rl algorithms
- control policy
- function approximators
- model free
- action space
- infinite horizon
- temporal difference
- approximate dynamic programming
- state and action spaces
- learning algorithm
- policy iteration
- transition model
- partially observable markov decision processes
- multi agent
- optimal control
- dynamic environments
- partially observable domains
- agent learns
- decision support
- state dependent
- control algorithm
- asymptotically optimal
- neural network
- temporal difference learning
- state action
- average reward
- path planning
- actor critic
- partially observable markov decision process
- reinforcement learning methods
- supervised learning
- mobile robot
- decision making