A Novel Variational Lower Bound for Inverse Reinforcement Learning.
Yikang GuiPrashant DoshiPublished in: CoRR (2023)
Keyphrases
- inverse reinforcement learning
- lower bound
- bayesian nonparametric
- upper bound
- partially observable environments
- preference elicitation
- worst case
- reward function
- image segmentation
- objective function
- optimal solution
- np hard
- temporal difference
- special case
- variational methods
- reinforcement learning
- generative model
- function approximation
- bayesian networks