Deep Adaptive Multi-Intention Inverse Reinforcement Learning.

Ariyan Bighashdel Panagiotis Meletis Pavol Jancura Gijs Dubbelman

Published in: CoRR (2021)

Keyphrases

inverse reinforcement learning
partially observable environments
bayesian nonparametric
preference elicitation
cost function
machine learning
learning algorithm
search algorithm
multi agent systems
probabilistic model
reward function