Hi, I’m using a custom environment, I was using stable-baslines3 for training but I’m trying to migrate to RLlib for scaling purposes. However after several training iterations, tuning hyperparams my model never converged to a result nearly as good as in the stabe-baselines3 and I tried to run a epi…

Hey @PatrickSampaioUSP , thanks for posting this issue. Would you be able to share your environment and config so we can take a look? It’s impossible to figure out why RLlib would not learn otherwise. Thanks.

Issue with custom environment

RLlib

mjlbach July 27, 2021, 12:09am 3

I have a reproduction in Issues reproducing stable-baselines3 PPO performance with rllib

Topic		Replies	Views
Reproducing results from stablebaselines 3 RLlib	2	708	August 6, 2021
Unable to replicate original PPO performance RLlib	0	234	May 10, 2024
Num_env & agent_steps_trained 0 even though steps sampled? RLlib	7	993	April 25, 2024
Issues reproducing stable-baselines3 PPO performance with rllib RLlib	14	2988	March 16, 2022
MultiAgent training Issues RLlib	1	615	April 9, 2024

Issue with custom environment

Related topics