Inferring Preferences from Demonstrations in Multi-objective Reinforcement Learning: A Dynamic Weight-based Approach.
Junlin LuPatrick MannionKarl MasonPublished in: CoRR (2023)
Keyphrases
- multi objective
- reinforcement learning
- multiple objectives
- optimization algorithm
- multi objective optimization
- multiple criteria
- genetic algorithm
- multi objective optimization problems
- multiobjective optimization
- dynamic environments
- individual preferences
- machine learning
- evolutionary optimization
- multi attribute
- function approximation
- user preferences
- evolutionary algorithm
- markov decision processes
- optimal policy
- model free
- particle swarm optimization
- simulated annealing
- dynamic programming