Finite-Sample Bounds for Adaptive Inverse Reinforcement Learning Using Passive Langevin Dynamics.
Luke SnowVikram KrishnamurthyPublished in: CDC (2023)
Keyphrases
- finite sample
- inverse reinforcement learning
- sample size
- statistical learning theory
- uniform convergence
- error bounds
- nearest neighbor
- generalization bounds
- parzen window
- upper bound
- model selection
- sufficient conditions
- vc dimension
- random variables
- machine learning
- generalization error
- upper and lower bounds
- support vector machine
- knn