Finite-Sample Bounds for Adaptive Inverse Reinforcement Learning using Passive Langevin Dynamics.
Luke SnowVikram KrishnamurthyPublished in: CoRR (2023)
Keyphrases
- finite sample
- inverse reinforcement learning
- sample size
- uniform convergence
- statistical learning theory
- error bounds
- nearest neighbor
- generalization bounds
- preference elicitation
- parzen window
- generalization error
- statistical learning
- upper bound
- machine learning
- worst case
- risk minimization
- theoretical framework
- special case