Autonomous Assessment of Demonstration Sufficiency via Bayesian Inverse Reinforcement Learning.
Tu TrinhHaoyu ChenDaniel S. BrownPublished in: HRI (2024)
Keyphrases
- inverse reinforcement learning
- bayesian nonparametric
- partially observable environments
- preference elicitation
- reward function
- bayesian networks
- reinforcement learning
- maximum likelihood
- gaussian processes
- decision theory
- posterior distribution
- mixture model
- privacy preserving
- maximum entropy
- gaussian process
- temporal difference