Passivizing learned policies and learning passive policies with virtual energy tanks in robotics.
Riccardo ZanellaGianluca PalliStefano StramigioliFederico CalifanoPublished in: CoRR (2023)
Keyphrases
- learning process
- policy gradient methods
- artificial intelligence
- inductive inference
- knowledge acquisition
- prior knowledge
- supervised learning
- collaborative learning
- unsupervised learning
- virtual environment
- learning problems
- online learning
- predictive state representations
- learning analytics
- neural network
- active learning
- computer vision
- learning algorithm