Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes.
He WangLaixi ShiYuejie ChiPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- sample complexity
- finite state
- optimal policy
- state space
- transition matrices
- policy iteration
- theoretical analysis
- upper bound
- reinforcement learning
- decision theoretic planning
- learning algorithm
- active learning
- supervised learning
- dynamic programming
- special case
- robust optimization
- learning problems
- infinite horizon
- lower bound
- upper and lower bounds
- partially observable
- action space
- generalization error
- data mining
- stochastic shortest path
- average cost
- dynamical systems
- support vector machine
- multi agent
- decision trees