Comments (5)
The reason for this error is that the ACKTR implementation we borrowed from https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail is not robust enough. Three suggestions to solve this problem:
- Increase the value of the mask (in config.py) during training.
- Modify the hyperparameters in the algorithm so that the training algorithm can avoid this convergence error.
- This convergence problem only appears in the implementation of ACKTR, you can try to change the training algorithm to a2c or other reinforcement learning algorithms.
from online-3d-bpp-drl.
Thank you I will try with these parameters.
from online-3d-bpp-drl.
The reason for this error is that the ACKTR implementation we borrowed from https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail is not robust enough. Three suggestions to solve this problem:
- Increase the value of the mask (in config.py) during training.
- Modify the hyperparameters in the algorithm so that the training algorithm can avoid this convergence error.
- This convergence problem only appears in the implementation of ACKTR, you can try to change the training algorithm to a2c or other reinforcement learning algorithms.
Hi @alexfrom0815
If I use a2c instead of ACKTR will there be any performance downside? Or its ok to use it
from online-3d-bpp-drl.
The reason for this error is that the ACKTR implementation we borrowed from https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail is not robust enough. Three suggestions to solve this problem:
- Increase the value of the mask (in config.py) during training.
- Modify the hyperparameters in the algorithm so that the training algorithm can avoid this convergence error.
- This convergence problem only appears in the implementation of ACKTR, you can try to change the training algorithm to a2c or other reinforcement learning algorithms.
Hi @alexfrom0815 If I use a2c instead of ACKTR will there be any performance downside? Or its ok to use it
Unfortunately, the a2c algorithm is indeed much worse than ACKTR. We are currently looking for better alternatives to the ACKTR algorithm. We encourage you to try some other algorithmic hyperparameters to avoid this ACKTR error (random seed, mask value, etc.).
Another tip is that although we cannot determine the cause of this error, from experience, when the error appears, the performance of the algorithm is generally close to the highest value, so its existence may not affect the final effect of the algorithm in a certain sense.
In addition, we have completed the implementation of a new online BPP algorithm, which is more stable than the current algorithm and can work at arbitrary resolution. Due to the double-blind protocol of the paper review, we will publish the new algorithm code after our new work is accepted.
from online-3d-bpp-drl.
The reason for this error is that the ACKTR implementation we borrowed from https://github.com/ikostrikov/pytorch-a2c-ppo-acktr-gail is not robust enough. Three suggestions to solve this problem:
1. Increase the value of the mask (in config.py) during training. 2. Modify the hyperparameters in the algorithm so that the training algorithm can avoid this convergence error. 3. This convergence problem only appears in the implementation of ACKTR, you can try to change the training algorithm to a2c or other reinforcement learning algorithms.
where is config.py? I did not find it.
from online-3d-bpp-drl.
Related Issues (20)
- ModuleNotFoundError: No module named 'baselines.common.vec_env.shmem_vec_env' HOT 2
- When I enabled the rotation, program: "RuntimeError: CUDA error: device-side assert triggered HOT 2
- the training speed problem HOT 1
- EOFError at connection.py HOT 5
- visual graph HOT 2
- Learning Online-3D-BPP-DRL - Get amount of the used containers HOT 3
- Learning Online-3D-BPP-DRL - Get amount of the used containers HOT 1
- Extrapolating to 4D HOT 1
- How to map to real-world data? HOT 1
- Unable to access or Execute the env files bin3D.py HOT 2
- BrokenPipeError HOT 7
- Are there something wrong with readme? HOT 3
- How to run the code with a2c HOT 2
- [Paper] Is Figure 2 (left) correct?
- a mistake that can not solve
- gym registration HOT 9
- ValueError: cannot reshape array of size 1600 into shape (10,10) HOT 7
- RuntimeError: CUDA out of memory. HOT 1
- RuntimeError: Error(s) in loading state_dict for Policy: size mismatch for base.critic_linear.bias HOT 3
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 online-3d-bpp-drl.