Antonin RAFFIN

Hello, thanks for providing the code =) Do you need any help to get it to work? I would be happy to link it in our doc (and maybe integrate...

Hello, >Which adjustments can I do to make it work properly? Have you tried other algorithms? Hyperparameter tuning? (included in the zoo, or you can have a look at https://araffin.github.io/post/hyperparam-tuning/)

By the way, what do you mean exactly by solving? a reward always equal to 1?

> Solving the environment equals to reaching the finish state. yes, but always or at least in some cases? Also the env is supposed to be deterministic, I've observed stochastic...

> I still have no clue why a simpler algorithm is able to perform better than A2C which it's supposed to be a better one. simpler doesn't mean worse, tabular...

With those commands, I managed to get ~60% success. `a2c.yaml`: ```yaml FrozenLake-v1: n_timesteps: !!float 1e6 policy: 'MlpPolicy' n_envs: 8 ```` ``` CUDA_VISIBLE_DEVICES= OMP_NUM_THREADS=1 python3 -m rl_zoo3.train --algo a2c --env FrozenLake-v1...

Hello, ```python try: model.learn(total_timesteps=10_000, progress_bar=True) except: # Cause Rich error model.learn(total_timesteps=2_000, progress_bar=True) ``` why would you do such thing? It looks like you should catch the exception inside the environment...

> What you posted is a workaround It is definitely a workaround but I would say it fits the provided code (which looks also like a workaround). This is what...

@vmoens you might have a look at https://github.com/DLR-RM/stable-baselines3/blob/feat/gymnasium-support/stable_baselines3/common/vec_env/patch_gym.py With this piece of code, we support gym 0.21/0.26 and gymnasium (using Gymnasium/vec env as primary backend). EDIT: i have some additionnal...

> It would be interesting to provide that method with the last observation object, isn't it? I am thinking about a game that has some logic that we want to...