Inverse reinforcement learning through logic constraint inference.
Mattijs BaertSam LerouxPieter SimoensPublished in: Mach. Learn. (2023)
Keyphrases
- inverse reinforcement learning
- bayesian nonparametric
- partially observable environments
- preference elicitation
- reward function
- variational inference
- mixture model
- probabilistic inference
- gaussian process
- bayesian networks
- bayesian inference
- decision making
- reinforcement learning
- decision makers
- temporal difference