Comments (13)
Hello @watashihageteru this work is based on developing learning algorithms that can leverage the information from demonstrations to speed up the learning process. However if you wish to train your algorithm without the demonstration data you can try to put "num_demonstrations = 0", but I think there are some parts of the code that have to be commented out still.
from overcoming-exploration-from-demos.
Hello @watashihageteru this work is based on developing learning algorithms that can leverage the information from demonstrations to speed up the learning process. However if you wish to train your algorithm without the demonstration data you can try to put "num_demonstrations = 0", but I think there are some parts of the code that have to be commented out still.
Can you send your files with demonstrations? And please explain how to debug this:
File "/home/khurram/DL_skoltech/Research_hand/HER_overcoming_exploration/experiment/ddpg.py", line 155, in initDemoBuffer
demoData = np.load(demoDataFile)
File "/home/khurram/.local/lib/python3.6/site-packages/numpy/lib/npyio.py", line 422, in load
fid = open(os_fspath(file), "rb")
IsADirectoryError: [Errno 21] Is a directory: '/home/khurram/DL_skoltech/'
from overcoming-exploration-from-demos.
Hello @KhurramPirov I have sent the demo file to your email.
About the error I think it's because you are not giving the correct path to the demo .npz file you might want to try something like /home/khurram/DL_skoltech/data_fetch_random_100.npz
in the train.py file.
from overcoming-exploration-from-demos.
You need demoData = np.load(demoDataFile, allow_pickle=True)
to get through the errors
from overcoming-exploration-from-demos.
Hello @jangirrishabh @KhurramPirov , can you share the demo file ?. Thank you.
from overcoming-exploration-from-demos.
Hello @jangirrishabh @KhurramPirov , can you share the demo file ? Thank you
from overcoming-exploration-from-demos.
Hello @jangirrishabh @KhurramPirov , can you share the demo file ? Thank you
from overcoming-exploration-from-demos.
Hello, you can generate the demo file by running the python script located in data_generation/fetch_data_generation.py
Check out the file contents for more information, hope it helps
from overcoming-exploration-from-demos.
Oh,I have find it, thanks a lot
from overcoming-exploration-from-demos.
@jnyanghit Hello! I am a chinese graduate student and reproducing the experiment's results. I want to communicate with you about it. Sorry for any interruption.
from overcoming-exploration-from-demos.
Hello @jangirrishabh @KhurramPirov , thanks for sharing the demo file. I need it urgently, please.
from overcoming-exploration-from-demos.
@jangirrishabh Hello, how to get the demos of the GazeboWAMemptyEnv-v1
from overcoming-exploration-from-demos.
@KhurramPirov @chaiban @jnyanghit Excuse me, how to deal with the env of GazeboWAMemptyEnv-v1? For example, how to get the demo of the env or how to import the env?
from overcoming-exploration-from-demos.
Related Issues (7)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from overcoming-exploration-from-demos.