Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments.
Jakob ThummMatthias AlthoffPublished in: ICRA (2022)
Keyphrases
- reinforcement learning
- human operators
- robot behavior
- robotic systems
- manipulation tasks
- real time
- mobile robot
- machine learning
- unstructured environments
- worst case
- dynamic programming
- function approximation
- real world
- human interaction
- human activities
- temporal difference
- physical world
- service robots
- perception action
- human subjects
- human robot interaction
- model free
- markov decision processes
- robot control
- dynamic environments
- learning process
- genetic algorithm
- multi agent environments
- robotic tasks
- robotic control