Reinforcement Learning of Pareto-Optimal Multiobjective Policies Using Steering.
Peter VamplewRustam IssabekovRichard DazeleyCameron FoalePublished in: Australasian Conference on Artificial Intelligence (2015)
Keyphrases
- pareto optimal
- multi objective
- reinforcement learning
- optimal policy
- multi objective optimization
- nsga ii
- policy search
- evolutionary algorithm
- multiple objectives
- optimization algorithm
- markov decision process
- multiobjective optimization
- state space
- pareto optimal set
- objective function
- markov decision processes
- pareto optimality
- pareto dominance
- genetic algorithm
- pareto optimal solutions
- multi issue negotiation
- pareto set
- reward function
- conflicting objectives
- particle swarm optimization
- dynamic programming
- multi objective optimization problems
- multi objective evolutionary algorithms
- multi agent
- multi criteria
- trade off
- social welfare
- multi agent systems
- neural network