Welfare and Fairness in Multi-objective Reinforcement Learning.
Zimeng FanNianli PengMuhang TianBrandon FainPublished in: AAMAS (2023)
Keyphrases
- multi objective
- reinforcement learning
- evolutionary algorithm
- optimization algorithm
- multi objective optimization
- function approximation
- multiobjective optimization
- particle swarm optimization
- conflicting objectives
- objective function
- genetic algorithm
- multiple objectives
- machine learning
- temporal difference
- state space
- reinforcement learning algorithms
- resource allocation
- markov decision processes
- robotic control
- learning process
- multi objective optimization problems
- nsga ii
- temporal difference learning
- model free
- multi objective evolutionary
- multi objective problems
- evolutionary optimization
- learning algorithm
- multi criteria
- action selection
- pareto optimal
- multi agent
- optimal control
- optimal solution
- policy search
- optimum design
- differential evolution
- evolutionary computation
- optimal policy