Off-Policy Evaluation of Slate Policies under Bayes Risk.
Nikos VlassisFernando Amat GilAshok ChandrashekarPublished in: CoRR (2021)
Keyphrases
- bayes risk
- policy evaluation
- optimal policy
- least squares
- partially observable markov decision processes
- policy iteration
- reinforcement learning
- monte carlo
- temporal difference
- markov decision processes
- loss function
- model free
- markov decision problems
- variance reduction
- function approximation
- markov decision process
- state space
- reproducing kernel hilbert space
- infinite horizon
- finite state
- dynamic programming
- posterior probability
- support vector
- image sequences