Opponent Modelling for Reinforcement Learning in Multi-Objective Normal Form Games.
Yijie ZhangRoxana RadulescuPatrick MannionDiederik M. RoijersAnn NowéPublished in: AAMAS (2020)
Keyphrases
- multi objective
- reinforcement learning
- evolutionary algorithm
- multi objective optimization
- optimization algorithm
- objective function
- function approximation
- genetic algorithm
- multiple objectives
- multi objective optimization problems
- state space
- pareto optimal
- special case
- multi agent
- machine learning
- nsga ii
- game theoretic
- nash equilibria
- dynamic programming
- agent receives