PyFlyt - UAV Simulation Environments for Reinforcement Learning Research.
Jun Jet TaiJim WongMauro S. InnocenteNadjim HorriJames BruseySwee King PhangPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- dynamic environments
- learning algorithm
- real world
- real robot
- simulation model
- simulation study
- function approximation
- markov decision processes
- unmanned aerial vehicles
- multi agent
- optimal control
- reinforcement learning algorithms
- robocup soccer
- real environment
- robot control
- multi agent reinforcement learning
- simulation models
- highly dynamic
- complex environments
- control algorithm
- robotic systems
- computing environments
- radial basis function
- optimal policy
- supervised learning
- state space