Mixing Probabilistic and non-Probabilistic Objectives in Markov Decision Processes.

Raphaël Berthon Shibashis Guha Jean-François Raskin

Published in: CoRR (2020)

Keyphrases

markov decision processes
bayesian networks
state space
probabilistic model
generative model
finite state
probabilistic planning
reinforcement learning
optimal policy
planning under uncertainty
dynamic programming
multistage
finite horizon