gxywy / rl-plotter Goto Github PK

:sparkles: A plotter for reinforcement learning (RL)

License: MIT License

Python 100.00%

plotting plot reinforcement-learning learning-curves rl-plotter plotter spinningup openai pytorch deep-rl

rl-plotter's Issues

Some questions about the Label；

Thanks for the effort in developing this wonderful tool.
I have some questions about the Label，as showing in the picture,

How can I remove the number of seed (is (5) in the picture) in the label?

Examples

Dear Author,

Thanks for your code for plotting, this helps a lot. But I am little confused by the average group function. Could you provide a example of logs, which can be used to plot the figure example you showed in 2. Practical Example in README.

Best,
Xinrun

Seed and Group

请问作者大大：
RL的试验不是应该是对不同种子求std或err嘛，为什么工具里默认是对不同种子的试验分开了要怎么画一起呢?
例如：
logs:
-exp_env_seed0-0
file.csv
-exp_env_seed1-0
file.csv

怎么对不同种子的结果求平均。
而不是只能对：
logs:
-exp_env_seed0-0
file.csv
-exp_env_seed0-1
file.csv
同一个种子的试验求平均

Could you please add the way to deal with rewards with same steps in a multi processes training?

In my training process, I use a multi-processes PPO.
When I want to draw the reward curve with rl-plotter, I found that:

Just like the image, there are rewards with the same steps. But it seems that it only shows one point in the curve?