A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines.

Weichao Zhou Wenchao Li

Published in: ICML (2022)

Keyphrases

inverse reinforcement learning
partially observable environments
bayesian nonparametric
reward function
preference elicitation
temporal difference
reinforcement learning
partially observable
optimal policy
machine learning
decision making
multi objective
evaluation function
reinforcement learning algorithms