Near-Optimal Sample Complexity Bounds for Constrained MDPs.
Sharan VaswaniLin F. YangCsaba SzepesváriPublished in: CoRR (2022)
Keyphrases
- sample complexity bounds
- average case
- sample complexity
- markov decision processes
- reinforcement learning
- partially observable markov decision processes
- state space
- covering numbers
- upper bound
- dynamic programming
- optimal policy
- theoretical analysis
- learning algorithm
- uniform distribution
- finite state
- worst case
- utility function
- decision problems
- vc dimension
- np hard
- markov decision problems
- small number