On Confident Policy Evaluation for Factored Markov Decision Processes with Node Dropouts.
Carmel FisckoSoummya KarBruno SinopoliPublished in: CDC (2022)
Keyphrases
- policy evaluation
- factored markov decision processes
- markov decision problems
- reinforcement learning
- least squares
- policy iteration
- state space
- temporal difference
- markov decision processes
- linear programming
- monte carlo
- model free
- function approximation
- partially observable
- optimal policy
- variance reduction
- utility function
- decision theoretic
- reinforcement learning algorithms
- queueing networks
- partially observable markov decision processes
- action space
- state variables
- probability distribution
- objective function
- learning algorithm