Maybe we should change this quickstart to not use A2C from rlberry but use instead stable-baselines3 agent from expermient manager.
A posteriori we could include @JulienT01 #395 work on fetching benchmarks from sb3 zoo in this quickstart. The core idea is to show how rlberry used in conjunction with stable-baselines3 can produce a full reproducible and fair comparisons research pipeline.
Maybe we should change this quickstart to not use A2C from rlberry but use instead stable-baselines3 agent from expermient manager. A posteriori we could include @JulienT01 #395 work on fetching benchmarks from sb3 zoo in this quickstart. The core idea is to show how rlberry used in conjunction with stable-baselines3 can produce a full reproducible and fair comparisons research pipeline.