Sign in
Manifold-based multi-objective policy search with sample reuse.
Simone Parisi
Matteo Pirotta
Jan Peters
Published in:
Neurocomputing (2017)
Keyphrases
</>
multi objective
policy search
evolutionary algorithm
reinforcement learning
multi objective optimization
objective function
continuous state
genetic algorithm
multiple objectives
continuous action
reinforcement learning algorithms
sample size
nsga ii
feature space
reward function