Antonin RAFFIN comments

Results 880 comments of


                                            Antonin RAFFIN

Multiple models for optimization

I couldn't push to your branch, so I created one here: https://github.com/DLR-RM/rl-baselines3-zoo/tree/feat/multi-model-optimization...

Multiple models for optimization

@qgallouedec could you open a draft PR with this updated branch? (so we keep a trace of it)

Fix issue #275: training=False needed for eval envs

thanks for the PR, overall LGTM =) i will do some quick tests (check that it doesn't affect results) when I'm back from holidays next week ;) (you can also...

Fix issue #275: training=False needed for eval envs

*affect results too much (that the change in performance is unnoticable)

Fix issue #275: training=False needed for eval envs

I did a quick check and change was as expected unnoticeable. See below, A2C on HalfCheetahBulletEnv-v0, same seed (so training stats are the same), I plotted the evaluation curve for...

Fix issue #275: training=False needed for eval envs

@pchalasani did you check "allow edit from maintainers"? I cannot push to your branch....

Fix issue #275: training=False needed for eval envs

weird, then could you give me access to your fork (at least temporary) so I can push the edits?

Bug in make type script?

Hello, Have you tried running it using the docker image? I couldn't reproduce the error locally (and the github action seems to work too). Could you provide your config? My...

[feature request] make rl-baselines3-zoo a python package

Hello, so that question was already asked in https://github.com/araffin/rl-baselines-zoo/issues/107 and https://github.com/DLR-RM/rl-baselines3-zoo/issues/53 I guess what you would like to access is the loading utils from `utils/` folder? (that is also in...

[feature request] Add retry failed trial callback to optuna study

Hello, > would like to suggest adding this to the cli command too. how would you like it to be done? by passing an argument `--retry-failed-trial`? and what is your...