Single Reinforcement Learning Policy for Landing a Drone Under Different UGV Velocities and Trajectories.
José AmendolaLinga Reddy CenkeramaddiAjit JhaPublished in: ICCMA (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- moving objects
- markov decision process
- function approximation
- action selection
- reinforcement learning problems
- control policy
- markov decision processes
- approximate dynamic programming
- state space
- optical flow
- learning algorithm
- neural network
- dynamic environments
- reinforcement learning algorithms
- sufficient conditions
- multiple targets
- spatio temporal