Polybot: Training One Policy Across Robots While Embracing Variability.
Jonathan YangDorsa SadighChelsea FinnPublished in: CoRR (2023)
Keyphrases
- multi robot
- mobile robot
- training process
- test set
- cooperative
- training examples
- tactile sensing
- autonomous robots
- humanoid robot
- training samples
- training set
- supervised learning
- optimal policy
- software engineering
- robotic systems
- hidden markov models
- learning algorithm
- genetic algorithm
- training phase
- robot soccer
- data sets