Comments (6)
I used a larger batch size (128) in my a3c implementation instead of 5 and it works quite well. I don't think there is any reason the batch size should be small. But that doesn't mean t_max should be large.
With a large t_max, the training gets less stable in my experiments.
from async-rl.
I don't understand how the batch can be large and t-max small? You need to accumulate frames during t-max steps before doing a backprop right?
from async-rl.
In one backprop you can accumulate more frames from different simulators, but each simulator still only produces a 5-step temporal difference every time. Having a larger batch size should theoretically stabilize training.
from async-rl.
Ah! Agreed. So like we should share a common replay memory to all threads and we recompute forward before large batch update?
from async-rl.
The forward part doesn't really need to be recomputed. A delay in the target value is acceptable, similar to the idea of target network in DQN.
from async-rl.
How can you run the project normally? I tried to run it but come out an error #12 . @ppwwyyxx @etienne87
from async-rl.
Related Issues (20)
- clipping
- How to speed up training with GPU?
- ValueError: Filter must not be larger than the input: Filter: (8, 8) Input: (4, 84) HOT 3
- Intel MKL FATAL ERROR: Cannot load libmkl_avx2.so or libmkl_def.so. HOT 3
- ValueError: need more than 4 values to unpack HOT 2
- About the randomness of the performance
- FailedPreconditionError HOT 4
- null
- May I know the version of keras and tensorflow? HOT 1
- Reward doesn't go up ....
- No local network synchronization
- Tensorflow outdated HOT 1
- Attempting to use uninitialized value conv2d_1/kernel HOT 9
- RGB image HOT 4
- duplicate
- about epsilon
- OSError,why?
- Stop actor gradient flowing through the critic HOT 2
- Do results differ only because of the seed?
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 async-rl.