A Policy Iteration Approach for Flock Motion Control.
Shuzheng QuMohammed I. AbouheafWail GueaiebDavide SpinelloPublished in: ROSE (2021)
Keyphrases
- motion control
- policy iteration
- markov decision processes
- mobile robot
- model free
- control system
- least squares
- reinforcement learning
- fixed point
- sample path
- robot control
- optimal policy
- autonomous robots
- finite state
- markov decision process
- physical constraints
- temporal difference
- infinite horizon
- autonomous navigation
- visual servoing
- linear programming
- control algorithm
- optimal control
- real robot
- state space
- average cost
- neural network
- convergence rate
- real world
- closed loop
- action space
- basis functions
- sufficient conditions