search

LucasAlegre / morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.
https://lucasalegre.github.io/morl-baselines
MIT License
271 stars 44 forks source link

Dev eupg #99

Closed omidsbhn closed 4 months ago

omidsbhn commented 4 months ago

In this version, I modified the scalarization function to work with vector values. In addition, by introducing _forward_cumulative_rewards method, the discounting factor is used when calculating the scalarized values.

ffelten commented 4 months ago

Hi @omidsbhn, Could you please fix the pre-commit issues and then we can merge this :)