Parameter-Independent Strategies for pMDPs via POMDPs.

Sebastian Arming Ezio Bartocci Krishnendu Chatterjee Joost-Pieter Katoen Ana Sokolova

Published in: QEST (2018)

Keyphrases

reinforcement learning
parameter values
partially observable markov decision processes
partially observable stochastic games
input parameters
parameter space
parameter settings
optimal strategy
real time
linear programming
continuous state