Nonlinear Multi-objective Reinforcement Learning with Provable Guarantees.
Nianli PengBrandon FainPublished in: CoRR (2023)
Keyphrases
- multi objective
- reinforcement learning
- evolutionary algorithm
- multi objective optimization
- objective function
- optimization algorithm
- multiple objectives
- function approximation
- genetic algorithm
- particle swarm optimization
- multiobjective optimization
- approximation guarantees
- bi objective
- model free
- machine learning
- evolutionary optimization
- conflicting objectives
- multi objective optimization problems
- nsga ii
- learning algorithm
- markov decision processes
- multiobjective evolutionary algorithm
- temporal difference
- reinforcement learning algorithms
- multi objective genetic algorithms
- approximation algorithms
- state space
- supervised learning
- optimal policy
- markov decision process
- theoretical guarantees
- simulated annealing
- decision making
- action selection
- transfer learning
- robotic control
- multi objective evolutionary
- pareto optimal