Staircase Traversal via Reinforcement Learning for Active Reconfiguration of Assistive Robots.
Andrei MitriakovPanagiotis PapadakisSao Mai NguyenSerge GarlattiPublished in: FUZZ-IEEE (2020)
Keyphrases
- reinforcement learning
- autonomous robots
- robotic control
- robot control
- mobile robot
- real robot
- function approximation
- imitation learning
- multi robot
- learning algorithm
- optimal policy
- data structure
- optimal control
- multi agent systems
- machine learning
- robotic agents
- image processing
- reinforcement learning algorithms
- model free
- human robot interaction
- learning process
- manufacturing systems
- human computer interaction
- state space
- smart environments
- dynamic programming
- robotic systems
- multi agent
- multi robot systems
- markov decision processes
- mobile phone