Comments (3)
On environment that do not require CNN, that is to be expected.
The GPU advantage seems to only kick in when the data / network size crosses a certain threshold,
namely where the overhead of moving the data to the GPU is negligible when compared to the cost of doing the feed forward as well as back propagation operations.
The following Wandb report only investigates the batch size, but the cuda=True
version seems to become overcome the CPU version around batch size ~7500:
https://app.wandb.ai/dosssman/cleanrl-cpu-gpu-comp/reports/Time-taken-w.r.t.-device--VmlldzoxMzIwNzE
Just to be sure, still need to check without the Wandb logging to make sure it is consistent without the logging overhead.
from cleanrl.
Well, turns out the Wandb overhead seems to really mess up the results.
When running the experiments with source code on a tmpfs device, the GPU version catches up even faster to the CPU one.
Although incomplete at the time of this writing, the following Wandb Report shows that GPU starts showing faster runtime than CPU from ~512 batch size:
https://app.wandb.ai/dosssman/cleanrl-cpu-gpu-comp-2/reports/Untitled-Report--VmlldzoxMzI0NjU
from cleanrl.
This has largely been fixed with the latest commits. Closing the issue for now.
from cleanrl.
Related Issues (20)
- Pyyaml error on poetry install HOT 10
- Question about the `noise-clip` parameter in DDPG. HOT 2
- Is is possible for SAC to support gymnasium too as TD3 and PPO ? HOT 4
- Poor Evaluation Performance in PPO HOT 5
- get action in sac_continuous_action.py HOT 2
- [BUG] Different final epsilon and evaluation epsilon for Atari implementations
- expected sequence of length 8 at dim 1 (got 0) HOT 4
- [BUG] Env does not reset when it's terminated HOT 2
- can't upload video running ppo_atari.py,wandb has no data HOT 8
- Why converting observation space to np.float32? HOT 2
- Reproduction util: wrong command path
- Why normarlize advantage only for pg_loss but not for vf_loss? HOT 1
- Contributing PPO + Transformer-XL HOT 3
- clamp in C51
- Gymnasium Version Requirement May Need To Be Updated HOT 1
- Gymnasium and PyBullet envs: Problem with video capture
- Docker image is out of date
- KeyError: 'cleanba_ppo_envpool_procgen'
- Unable to allocate 26.3 GiB for an array HOT 1
- Potential bugs in RecordEpisodeStatistics
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 cleanrl.