Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning.
Shuang QiuDake ZhangRui YangBoxiang LyuTong ZhangPublished in: CoRR (2024)
Keyphrases
- multi objective
- pareto optimal
- reinforcement learning
- multi objective optimization
- nsga ii
- multiple objectives
- optimization algorithm
- evolutionary algorithm
- optimal policy
- pareto optimal set
- pareto set
- pareto optimality
- conflicting objectives
- objective function
- pareto optimal solutions
- genetic algorithm
- nash equilibrium
- multiobjective optimization
- particle swarm optimization
- multi issue negotiation
- pareto dominance
- bi objective
- optimum design
- policy search
- social welfare
- markov decision process
- learning algorithm
- multi criteria
- optimal solution
- cost function
- software agents
- state space
- worst case