• Corpus ID: 251105397

Accelerating the Learning of TAMER with Counterfactual Explanations

@inproceedings{Karalus2021AcceleratingTL,
  title={Accelerating the Learning of TAMER with Counterfactual Explanations},
  author={Jakob Karalus and F. Lindner},
  year={2021}
}
—The capability to interactively learn from human feedback would enable agents in new settings. For example, even novice users could train service robots in new tasks naturally and interactively. Human-in-the-loop Reinforcement Learning (HRL) combines human feedback and Reinforcement Learning (RL) techniques. State-of-the-art interactive learning techniques suffer from slow learning speed, thus leading to a frustrating experience for the human. We approach this problem by extending the HRL… 

Figures from this paper