Computational-Statistical Gap in Reinforcement Learning.
Daniel KaneSihan LiuShachar LovettGaurav MahajanPublished in: COLT (2022)
Keyphrases
- reinforcement learning
- function approximation
- statistical analysis
- learning algorithm
- databases
- markov decision processes
- statistical models
- state space
- data driven
- information theoretic
- robotic control
- dynamic programming
- linear programming
- neural network
- mathematical programming
- learning process
- decision trees
- computational models
- database
- statistical significance
- model free
- statistical approaches
- multi agent reinforcement learning