Control of an Unmanned Surface Vehicle Based on Adaptive Dynamic Programming and Deep Reinforcement Learning.
Alejandro González GarcíaDavid Barragan-AlcantarIvana Collado-GonzalezLeonardo GarridoPublished in: ICDLT (2020)
Keyphrases
- dynamic programming
- reinforcement learning
- autonomous vehicles
- optimal control
- control problems
- adaptive control
- state space
- markov decision processes
- robot control
- optimal policy
- control policy
- underwater vehicles
- control strategies
- control method
- coarse to fine
- surface reconstruction
- control system
- path planning
- traffic signal
- function approximation
- real time
- three dimensional
- control algorithm
- control strategy
- infinite horizon
- temporal difference
- pedestrian detection
- greedy algorithm
- linear programming
- d objects
- policy search
- mobile robot
- robotic control