Expectation Optimization with Probabilistic Guarantees in POMDPs with Discounted-Sum Objectives.
Krishnendu ChatterjeeAdrián ElgyüttPetr NovotnýOwen RouilléPublished in: IJCAI (2018)
Keyphrases
- markov decision processes
- multiple objectives
- optimization problems
- dynamic programming
- optimal policy
- infinite horizon
- optimization algorithm
- optimization methods
- optimization process
- bayesian networks
- simultaneous optimization
- generative model
- state space
- uncertain data
- probabilistic model
- reinforcement learning
- partially observable markov decision processes
- markov decision process
- planning under uncertainty
- min sum
- multi objective
- multi agent
- belief state
- partially observable
- initial state
- optimization criteria
- machine learning