LucasAlegre / morl-baselines

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

Fix GPI-LS name in Benchmark script #54

Closed ffelten closed 1 year ago

LucasAlegre commented 1 year ago

I may prefer leaving Dyna off by default, as it can be quite slow, although more sample efficient. Actually, the best option is to simply make a GPI-PD class that inherits GPI-LS and sets Dyna=True. I will do that.