Corrected: On Confident Policy Evaluation for Factored Markov Decision Processes with Node Dropouts.
Carmel FisckoSoummya KarBruno SinopoliPublished in: CoRR (2023)
Keyphrases
- policy evaluation
- factored markov decision processes
- markov decision problems
- reinforcement learning
- least squares
- policy iteration
- temporal difference
- markov decision processes
- state space
- monte carlo
- model free
- linear programming
- optimal policy
- variance reduction
- function approximation
- semi parametric
- partially observable
- utility function
- decision theoretic
- function approximators
- decision processes
- machine learning
- bayesian networks
- infinite horizon
- transition probabilities
- queueing networks
- evaluation function
- decision problems
- linear program
- markov chain
- supervised learning
- dynamic programming
- objective function
- neural network