Plot training rewards with different algorithms

[learningxiaobai]

trafficstars

❓ Question

Hello， If I want to plot training rewards with different algorithms about one Env, such as : python scripts/plot_train.py -a td3 sac ddpg -e PandaReach -f logs/ -w 500 -x steps but there is no code about these. Only one algorithm is provided: parser.add_argument("-a", "--algo", help="Algorithm to include", type=str, required=True) Do you have any ideas about these? Thanks!

Checklist

• [X] I have checked that there is no similar issue in the repo
• [X] I have read the SB3 documentation
• [X] I have read the RL Zoo README
• [X] If code there is, it is minimal and working
• [X] If code there is, it is formatted using the markdown code blocks for both code and stack traces.

[araffin]

Do you have any ideas about these? Thanks!

Hello, yes, this is a current limitation of the script but I would happy to receive a PR that add this feature.

[araffin]

in the meantime, you can (and should use) python scripts/all_plots which compare the evaluations and supports multiple algorithms at once.

[learningxiaobai]

Thanks, I will try.