Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm.
Miao LuHan ZhongTong ZhangJose H. BlanchetPublished in: CoRR (2024)
Keyphrases
- data collection
- dynamic programming
- np hard
- experimental evaluation
- times faster
- computationally efficient
- learning algorithm
- preprocessing
- reinforcement learning
- computational complexity
- optimization algorithm
- worst case
- model free
- detection algorithm
- parameter tuning
- segmentation algorithm
- optimal solution
- k means
- objective function
- high accuracy
- computational cost
- cost function
- least squares
- convergence rate
- object tracking algorithm
- monte carlo
- clustering method
- mobile robot
- search space
- similarity measure