Welfare and Fairness in Multi-objective Reinforcement Learning.
Zimeng FanNianli PengMuhang TianBrandon FainPublished in: CoRR (2022)
Keyphrases
- multi objective
- reinforcement learning
- multi objective optimization
- evolutionary algorithm
- optimization algorithm
- particle swarm optimization
- multiobjective optimization
- objective function
- conflicting objectives
- evolutionary optimization
- model free
- state space
- reinforcement learning algorithms
- multiple objectives
- pareto optimal
- function approximation
- learning algorithm
- bi objective
- multi objective optimization problems
- robotic control
- genetic algorithm
- transfer learning
- optimal policy
- machine learning
- action selection
- markov decision processes
- dynamic programming
- nsga ii
- learning problems
- multi criteria
- multiobjective evolutionary algorithm
- transition model
- supervised learning
- multi objective evolutionary
- trade off
- temporal difference learning
- function approximators
- multi objective evolutionary algorithms
- social welfare
- markov decision process
- temporal difference