Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning.
Willem RöpkeMathieu ReymondPatrick MannionDiederik M. RoijersAnn NowéRoxana RadulescuPublished in: CoRR (2024)
Keyphrases
- multi objective
- reinforcement learning
- multi objective optimization
- evolutionary algorithm
- optimization algorithm
- nsga ii
- multiobjective optimization
- genetic algorithm
- objective function
- multiple objectives
- particle swarm optimization
- state space
- pareto fronts
- machine learning
- multi objective optimization problems
- conflicting objectives
- multi objective evolutionary algorithms
- evolutionary optimization
- markov decision processes
- function approximation
- engineering design problems
- bi objective
- optimum design
- multiobjective evolutionary algorithm
- multi criteria
- pareto optimal
- model free
- optimal policy
- multi agent
- learning algorithm
- multi objective evolutionary
- pareto optimal solutions
- action selection
- optimal control
- dynamic programming
- evolutionary computation
- learning process
- trade off