Admissible Policy Teaching through Reward Design.

Kiarash Banihashem Adish Singla Jiarui Gan Goran Radanovic

Published in: AAAI (2022)

Keyphrases

virtual laboratory
reinforcement learning
hybrid learning
user interface
state space
online learning
distance education
learning design
cooperative learning
average reward
active participation
inverse reinforcement learning
learner centred