Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees.
Siliang ZengChenliang LiAlfredo GarciaMingyi HongPublished in: NeurIPS (2022)
Keyphrases
- inverse reinforcement learning
- maximum likelihood
- bayesian nonparametric
- partially observable environments
- preference elicitation
- reward function
- mixture model
- em algorithm
- expectation maximization
- maximum a posteriori
- gaussian distribution
- machine learning
- temporal difference
- hidden markov models
- monte carlo
- gaussian process