WFA-IRL: Inverse Reinforcement Learning of Autonomous Behaviors Encoded as Weighted Finite Automata.

Tianyu Wang Nikolay Atanasov

Published in: IROS (2022)

Keyphrases

inverse reinforcement learning
finite automata
bayesian nonparametric
partially observable environments
preference elicitation
grammatical inference
regular expressions
reward function
temporal difference
hidden markov models
probability distribution
pattern matching
utility function
evaluation function