Keyphrases
- reinforcement learning
- function approximation
- state space
- swarm intelligence
- dynamic programming
- particle swarm optimization
- robotic control
- reinforcement learning algorithms
- learning algorithm
- model free
- control algorithm
- optimal control
- machine learning
- vision based navigation
- optimal policy
- search space
- action selection
- cooperative
- real robot
- multi agent reinforcement learning
- unmanned aerial vehicles
- trajectory data
- markov decision processes
- evolutionary computation
- robot control
- temporal difference
- search and rescue
- learning process
- initially unknown
- path planning