Login / Signup
Multi-objective reinforcement learning for acquiring all Pareto optimal policies simultaneously - Method of determining scalarization weights.
Hitoshi Iima
Yasuaki Kuroe
Published in:
SMC (2014)
Keyphrases
</>
multi objective
reinforcement learning
optimal policy
dynamic programming
state space
markov decision processes
objective function
learning algorithm
evolutionary algorithm
convergence rate
multi objective optimization
finite state
multiobjective optimization
policy evaluation