Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning.
Yuanzhi LiRuosong WangLin F. YangPublished in: FOCS (2022)
Keyphrases
- sample complexity
- reinforcement learning
- learning problems
- learning algorithm
- supervised learning
- theoretical analysis
- pac learning
- upper bound
- vc dimension
- lower bound
- generalization error
- active learning
- special case
- pac learnability
- sample size
- state space
- concept classes
- average case
- sequential decision problems
- multi agent
- learning process
- optimal policy
- markov decision processes
- learning tasks
- training data
- training examples
- machine learning
- training set
- transfer learning
- feature extraction
- unsupervised learning
- small number
- irrelevant features