Dynamic Weights in Multi-Objective Deep Reinforcement Learning.

Axel Abels Diederik M. Roijers Tom Lenaerts Ann Nowé Denis Steckelmacher

Published in: CoRR (2018)

Keyphrases

multi objective
reinforcement learning
evolutionary algorithm
multi objective optimization
machine learning

multiple objectives
function approximation
linear combination
genetic algorithm

dynamic environments
markov decision processes
objective function
optimal control

data sets
temporal difference
bi objective
evolutionary optimization