Near-Optimal Sample Complexity Bounds for Constrained MDPs.
Sharan VaswaniLin YangCsaba SzepesváriPublished in: NeurIPS (2022)
Keyphrases
- sample complexity bounds
- sample complexity
- average case
- markov decision processes
- reinforcement learning
- covering numbers
- partially observable markov decision processes
- state space
- optimal policy
- dynamic programming
- uniform convergence
- small number
- planning problems
- finite state
- machine learning
- reward function
- partially observable
- markov decision problems