search

leekwoon / hrl-nav

[ICRA 2023] Adaptive and Explainable Deployment of Navigation Skills via Hierarchical Deep Reinforcement Learning
MIT License
94 stars 8 forks source link

about testing #5

Open Shiqi-7-7 opened 2 months ago

Shiqi-7-7 commented 2 months ago

Hello, thank you very much for your work. I have read your article and tried to reproduce code.This is the screen that appears after I input testing code： 2024-07-05 17-17-25 的屏幕截图 building.npy was generated 2024-07-05 17-41-43 的屏幕截图 I'm a novice,Can you give me some advice？ 1.How do I use building.npy 2.How do I obtain the curve graph during the training process and the charts in your paper

Thank you!

leekwoon commented 1 month ago

Hi @Shiqi-7-7,

To check the results of the simulation, I recommend you to examine env_infos.

For example, if you want to see the detailed results from the 1st rollout, you can check as follows (in your case):

import numpy as np

paths = np.load('building.npy', allow_pickle=True)
print(paths[0]['env_infos'][-1])