On the Correctness and Sample Complexity of Inverse Reinforcement Learning.
Abi KomanduruJean HonorioPublished in: NeurIPS (2019)
Keyphrases
- sample complexity
- inverse reinforcement learning
- theoretical analysis
- pac learning
- upper bound
- learning problems
- special case
- preference elicitation
- vc dimension
- active learning
- supervised learning
- learning algorithm
- generalization error
- lower bound
- reward function
- sample size
- training examples
- training data
- training set
- worst case
- learning process