On the Correctness and Sample Complexity of Inverse Reinforcement Learning.
Abi KomanduruJean HonorioPublished in: CoRR (2019)
Keyphrases
- sample complexity
- inverse reinforcement learning
- theoretical analysis
- learning problems
- vc dimension
- pac learning
- upper bound
- preference elicitation
- active learning
- special case
- learning algorithm
- lower bound
- supervised learning
- generalization error
- reward function
- sample size
- training examples
- temporal difference
- reinforcement learning
- model selection
- machine learning
- cross validation
- feature selection
- small number
- prior knowledge
- learning process