Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees.

Siliang Zeng Chenliang Li Alfredo Garcia Mingyi Hong

Published in: CoRR (2022)

Keyphrases

inverse reinforcement learning
maximum likelihood
bayesian nonparametric
partially observable environments
preference elicitation
mixture model
em algorithm
reward function
maximum a posteriori
gaussian distribution
expectation maximization
theoretical framework
monte carlo
temporal difference