Comments (11)
I believe the fixes that you have there are correct though.
from nocturne.
Hi @eugenevinitsky ,
Everything is running now thanks for the fixes.
Just out of curiosity before we close this issue, what should the fps be during training? I'm getting 25-30:
average episode rewards is 0.33026985824108124
maximum per step reward is 0.058307357132434845
Algo rmappo Exp intersection updates 50/1250000 episodes, total num timesteps 4080/100000000.0, FPS 29.
average episode rewards is 2.849382162094116
maximum per step reward is 8.059619903564453
episode reward of rendered episode is: 0.8622641801569368
Algo rmappo Exp intersection updates 55/1250000 episodes, total num timesteps 4480/100000000.0, FPS 25.
average episode rewards is 0.9344396740198135
maximum per step reward is 0.05804213136434555
Algo rmappo Exp intersection updates 60/1250000 episodes, total num timesteps 4880/100000000.0, FPS 26.
average episode rewards is 1.3483695685863495
maximum per step reward is 8.056236267089844
Algo rmappo Exp intersection updates 65/1250000 episodes, total num timesteps 5280/100000000.0, FPS 27.
average episode rewards is 1.1445978283882141
maximum per step reward is 0.057421959936618805
```
Thanks!
from nocturne.
Hi @eugenevinitsky ,
Everything is running now thanks for the fixes.
Just out of curiosity before we close this issue, what should the fps be during training? I'm getting 25-30:
average episode rewards is 0.33026985824108124 maximum per step reward is 0.058307357132434845 Algo rmappo Exp intersection updates 50/1250000 episodes, total num timesteps 4080/100000000.0, FPS 29. average episode rewards is 2.849382162094116 maximum per step reward is 8.059619903564453 episode reward of rendered episode is: 0.8622641801569368 Algo rmappo Exp intersection updates 55/1250000 episodes, total num timesteps 4480/100000000.0, FPS 25. average episode rewards is 0.9344396740198135 maximum per step reward is 0.05804213136434555 Algo rmappo Exp intersection updates 60/1250000 episodes, total num timesteps 4880/100000000.0, FPS 26. average episode rewards is 1.3483695685863495 maximum per step reward is 8.056236267089844 Algo rmappo Exp intersection updates 65/1250000 episodes, total num timesteps 5280/100000000.0, FPS 27. average episode rewards is 1.1445978283882141 maximum per step reward is 0.057421959936618805
Thanks!
It's hard to say what is the normal FPS. It depends on lost of things. Could you provide more details such as what machine you are using, what and how many CPU cores you have, what and how many GPUs you have, etc.
from nocturne.
We're going to re-open this because that's a good deal slower than we expect it to be. @xiaomengy, any chance you could run the line
python examples/on_policy_files/nocturne_runner.py algorithm=ppo algorithm.n_rollout_threads=4
and report the FPS? I don't have GPU access for a little while so I can't check it myself.
from nocturne.
@eugenevinitsky Could you help take a look?
from nocturne.
Hi, sorry this bug is here! I am out today but this will be definitively fixed by tomorrow afternoon.
from nocturne.
Thanks for your patience, working on getting this merged but the relevant fixes are in:
#39
from nocturne.
Heads up though, that code has not been extensively hyper-parameter tuned
from nocturne.
No rush at all but let us know if this resolves your issue?
from nocturne.
Hey @roggirg, it depends on the number of rollout threads you're using and whether you are using a GPU or just CPU; the MAPPO code uses an RNN by default and includes the time for backprop when computing the FPS. Can you try increasing the value of algorithm.n_rollout_threads? It should basically scale linearly in the number of threads or workers
from nocturne.
Ah cool, thanks @eugenevinitsky @xiaomengy . I played around with n_rollout_threads=4 (did not know of its existence) and the FPS jumped up to ~50ish.
FYI, I'm running on a 1080Ti with a 12 -core CPU.
Thanks for your help.
from nocturne.
Related Issues (20)
- Will the other cars in the simulation react to the ego agent's actions? HOT 9
- [Bug] Unexpected behavior when setting padding=True in scenario.visible_state() HOT 3
- [Feature] Pretrained agents HOT 2
- [Bug] Dependencies not listed in environment file HOT 1
- [Bug] Problem installing it on Windows 10 HOT 1
- [Bug] Mistake in continuous action space definition HOT 2
- [Question] Optimal hyperparameters and scripts to reach 2000 steps/sec training speed HOT 3
- Comparison of missing driving simulators in the nocturne paper[Question] HOT 3
- [Question] SFML/Graphics.hpp file not found HOT 4
- [Feature] Is it possible to support user-specific map? HOT 1
- [Feature] Don't install `cfgs` module as a top level Python import HOT 4
- [Question] How is the masking achieved? HOT 4
- [Question] Difference in active_masks copying in shared_buffer and separated_buffer files HOT 2
- [Question] How can I get the VisibleObjects? HOT 2
- The Dropbox abort the download HOT 4
- [Question] Compatibility with VectorNet HOT 8
- [Bug] APPO
- [Bug] python examples/imitation_learning/train.py HOT 1
- [Bug] eval_sample_factory.py
- [Question] How to import the provided expert trajectory and integrate it into the state?
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 nocturne.