On the limitations of Markovian rewards to express multi-objective, risk-sensitive, and modal tasks.

Joar Skalse Alessandro Abate

Published in: UAI (2023)

Keyphrases

multi objective
risk sensitive
markov decision processes
evolutionary algorithm
multi objective optimization
optimization algorithm
reinforcement learning
optimal control
genetic algorithm
utility function
optimal policy
objective function
multiple objectives
pareto optimal
np hard
nsga ii
markov decision problems