Costa Huang

Thank you! I tried running ``` def repr_fn(h: Hypothesis) -> pd.DataFrame: # A dummy function that manipulates the representative value ('median') df = cast(pd.DataFrame, h.grouped.median()) # df['loss'] = np.asarray(df.reset_index()['step']) *...

Hi @wookayin hope you are doing well. I remember you had a draft notebook with wandb. Would you mind sharing it with me? Thanks!

Just got the notebook. Thank you!

Thank you @wookayin. I have been playing with the plotting API and think it's well-designed and easy to use. I made some prototypes here https://github.com/openrlbenchmark/openrlbenchmark/pull/2. Totally understand you are busy...

请问，如果是container的话，为什么会不支持websocket呢？

感谢回复。这么神奇… 那为什么要拦截呢？

Hey, @yooceii would you mind reverting the formatting change? They make it harder to review and identify the code specifically relating to RND. Formatting change should be done in a...

## Refactor Check (compatible with the performance in the tracked experiment) I compared the SPS performance of the latest refactor against the [old script used in the tracked experiment](https://wandb.ai/openrlbenchmark/cleanrl/runs/1wm98fjm/code?workspace=user-costa-huang). I...

Hello, thanks for reporting. Could you check if your performance match the reported performance in the docs? https://docs.cleanrl.dev/rl-algorithms/dqn/#experiment-results_1 Basically the performance is not that great as I had found it...

Yeah it is unsatisfactory. We always welcome new contributors! If you are interested in trying out https://github.com/vwxyzjn/cleanrl/pull/228 to find a set of params that work well for `CartPole-v1`, `MountainCar-v0`, and...