The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm.
Giseung ParkWoohyeon ByeonSeongmin KimElad HavakukAmir LeshemYoungchul SungPublished in: CoRR (2024)
Keyphrases
- model free
- reinforcement learning
- max min
- multi objective
- reinforcement learning algorithms
- function approximation
- learning algorithm
- policy iteration
- convergence rate
- dynamic programming
- min max
- state space
- exhaustive search
- hill climbing
- objective function
- average reward
- linear programming
- optimal solution
- feature space
- search algorithm