Estimating Objective Weights of Pareto-Optimal Policies for Multi-Objective Sequential Decision-Making.
Akiko IkenagaSachiyo AraiPublished in: J. Adv. Comput. Intell. Intell. Informatics (2024)
Keyphrases
- multi objective
- sequential decision making
- optimal policy
- decision problems
- reinforcement learning
- multiple objectives
- influence diagrams
- multi objective optimization
- pareto optimal solutions
- evolutionary algorithm
- markov decision processes
- multiobjective optimization
- multi objective evolutionary algorithms
- optimization algorithm
- state space
- infinite horizon
- nsga ii
- finite horizon
- dynamic programming
- genetic algorithm
- optimal strategy
- long run
- pareto optimal
- particle swarm optimization
- objective function
- average reward
- policy iteration
- sufficient conditions
- average cost
- lost sales
- temporal difference
- reinforcement learning algorithms
- function approximation
- dynamic programming algorithms
- serial inventory systems
- np hard
- reward function
- optimal solution
- computational complexity
- average reward reinforcement learning