Inclusion of baseline results about rl-baselines-zoo HOT 3 CLOSED

Hello,

At a minimum, there should be information on a number of training steps

You have that in the hyperparameters file and the config file associated with each trained agent (at least starting with release 1.0 of the zoo). The final performance can be found in benchmark.md, note the results correspond only to one seed (it is not meant for quantitative comparison).

Yes, training curve would be a good addition, even better learning curve using a test env periodically (it is planned to be supported with the callback collection), but you would at least 10 runs per algorithm per environment.

it seems monitor.csv

Monitor.csv can give you the training learning curve, which is only a proxy to the real performance.

Furthermore, these files are not produced at all currently if you run the experiment.

If you don't specify a log folder, nothing is produced, yes.

from rl-baselines-zoo.

I think my comment is probably misunderstood. I'm currently trying to train model for Breakout and reproduce the results. There is nothing in this repo that tells me what I should expect and how do I know the training was successful. As it happens, something is possibly broken in OpenAI baselines as well as stable-baselines so the training for Breakout isn't generating graphs that are convincingly converging.

from rl-baselines-zoo.

Also, looks like in current codebase, there is no call to logger.configure() at all made when running training.py. This possibly explains why there are no monitor.csv and progress.csv generated even when log directory is specified.

from rl-baselines-zoo.