Actor-critic multi-objective reinforcement learning for non-linear utility functions.
Mathieu ReymondConor F. HayesDenis SteckelmacherDiederik M. RoijersAnn NowéPublished in: Auton. Agents Multi Agent Syst. (2023)
Keyphrases
- utility function
- actor critic
- multi objective
- reinforcement learning
- temporal difference
- evolutionary algorithm
- policy gradient
- reinforcement learning algorithms
- optimal control
- approximate dynamic programming
- decision makers
- neuro fuzzy
- optimization algorithm
- policy iteration
- gradient method
- function approximation
- objective function
- decision problems
- genetic algorithm
- state space
- decision theory
- probability distribution
- model free
- markov decision problems
- pareto optimal
- markov decision processes
- average reward
- multi agent
- transfer learning
- learning algorithm
- machine learning
- action selection
- learning problems
- differential evolution
- rl algorithms
- step size
- dynamic programming
- function approximators
- temporal difference learning
- monte carlo