search

LucasAlegre / morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.
https://lucasalegre.github.io/morl-baselines
MIT License
295 stars 47 forks source link

Feature/add eum #23

Closed ffelten closed 1 year ago

LucasAlegre commented 1 year ago

The only strange thing to me is that it receives the utility = np.dot as a parameter. I can not think of a use case where someone will pass a weight list, but not use np.dot.

ffelten commented 1 year ago

The only strange thing to me is that it receives the utility = np.dot as a parameter. I can not think of a use case where someone will pass a weight list, but not use np.dot.

@LucasAlegre In the case the user's utility follows a non linear setting.