Interaction-limited Inverse Reinforcement Learning

no code implementations • 1 Jul 2020 • Martin Troussard, Emmanuel Pignat, Parameswaran Kamalaruban, Sylvain Calinon, Volkan Cevher

This paper proposes an inverse reinforcement learning (IRL) framework to accelerate learning when the learner-teacher \textit{interaction} is \textit{limited} during training.

reinforcement-learning Reinforcement Learning (RL)