zhuzzq / edgefed-marl-mec Goto Github PK
View Code? Open in Web Editor NEWLicense: Apache License 2.0
License: Apache License 2.0
你好,请问我在运行maac_run 文件的时候提示缺少这个文件,请问这个怎么解决,谢谢您
epoch2073
Traceback (most recent call last):
File "e: /wuzhu/Documents/Visual Studio Code/EdgeFed-MARL-MEC-master/AC_run.py", line 88, in
AC. train(MAX_EPOCH, MAX_EP_STEPS, up_freq=up_freq, render=True, render_freq=render_freq)
File "e: \wuzhu\Documents\Visual Studio Code\EdgeFed-MARL-MEC-master\AC_agent.py", line 379, in train
cur_reward = self.actor_act (epoch)
File "e: \wuzhu\Documents \Visual studio Code\EdgeFed-MARL-MEC-master \AC_agent.py", line 243, in actor_act
move _ori = circle_argmax(move _dist, self.env.move_r)
File "e: \wuzhu\Documents \isual Studio Code\EdgeFed-MARL-MEC-master\AC_agent.py", line 156, in circle_argmax
return max_pos[np.argmin(pos_dist)]
File "< array functioninternals>", line 6, in argmin
"F: \anaconda3\envs\test\lib\site-packages \numpy\core\fromnumeric.py", line 1269, in argmin
return _wrapfunc(a,'argmin', axis=axis, out=out)
File "F: \anaconda3\envs\test\lib\site-packages\numpy\core\fromnumeric.py" line 58, in _wrapfunc
return bound (*args,**kwds)
ValueError: attempt to get argmin of an empty sequence
`
def circle_argmax(move_dist, move_r):
max_pos = np.argwhere(tf.squeeze(move_dist, axis=-1) == np.max(move_dist))
# print(tf.squeeze(move_dist, axis=-1))
pos_dist = np.linalg.norm(max_pos - np.array([move_r, move_r]), axis=1)
# print(max_pos)
return max_pos[np.argmin(pos_dist)]
`
Hello, when I was training your code, after the 2073rd round of training, I reported the above error. Have you encountered a similar error message? How was it resolved?
Hi,
I recently read your paper <Federated Multi-Agent Actor-Critic Learning for Age Sensitive Mobile Edge Computing* [J]. IEEE Internet of Things Journal, 2021> and am interested about your model. I have tried to simulate your code but have following questions:
Thank you very much for your time if you can answer my quries.
Dear Dr. Zhu,
I came across your research on deep reinforcement learning algorithms, specifically the use of Mixed DDPG and H-MAAC in multi-agent environments. I found your work on H-MAAC to be very interesting and insightful.
I am particularly interested in your research on multi-agent deep reinforcement learning and the use of the MADDPG algorithm. I understand that your current implementation only includes the MIxed DDPG and H-MAAC algorithms and would like to inquire if you also have code for the MADDPG algorithm.
If possible, may I request access to the MADDPG code that you have developed for your research? Your code can help me deepen my understanding of the MADDPG algorithm and its applications in multi-agent MEC environments. My email address is [email protected]
Thank you for your time and consideration. I look forward to hearing from you soon.
Best regards,
Haozhe li
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.