A Reinforcement Learning Approach to View Planning for Automated Inspection Tasks.
Christian LandgrafBernd MeeseMichael PabstGeorg MartiusMarco F. HuberPublished in: Sensors (2021)
Keyphrases
- reinforcement learning
- complex domains
- planning tasks
- action selection
- transfer learning
- multi agent environments
- function approximation
- multiple views
- partially observable
- goal oriented
- planning systems
- multiple tasks
- state space
- machine learning
- blocks world
- markov decision problems
- deterministic domains
- autonomous robots
- temporal difference
- data sets
- markov decision processes
- optimal policy
- d objects
- dynamic programming
- learning algorithm
- neural network