Comments (3)
Very common issue in machine learning in general. Some quick reading might show you suggestions like
Bayesian > random > gridsearch. That is a SUPER simple view, cause I have had seen many try Bayesian opt and fail, more so in architecture vs hyperparam opt.
I would DEF not opt things yourself or use a grid search. Just let it run via Spearmint for a few days to save your sanity.
https://github.com/HIPS/Spearmint
Of course this is just 1 quick, old idea. I'm sure there are many more cutting edge ways to explore the param space.
from deeprl-agents.
The Spearmint examples show how to place you code inside a function and then call it from another. This is used by Spearmint to automatically determine the best values for whatever you let it optimize.
For example you could set ranges for your: learning rate, skip rate, gamma and max experience buffer len, and then have Spearmint automatically, "intelligently"(Bayesian) explore the param space in a quicker way than a grid or random search might. The trick would be evaluation. You would have to take the max of the average score or some other grading factor to judge each experiment against each other in a meaningful way. If you use multi factors you could try minimizing (-top score, time to score) and try to discover a network that works best for you. The idea being even if it took a month its totally automatic. Smartish Brute force, woooo!
If you have the resources, Spearmint can speed up its efforts by running multiple experiments at once.
from deeprl-agents.
@DMTSource thank you, helpful as usual :)
Moreover, I have seen the following
This short video
and this nice article
What are super simple ways to perform optimization like Spearmint? I mean that will be applied to the code easily (This TensorFlow "DeepRL-Agents" code)
from deeprl-agents.
Related Issues (20)
- _ HOT 1
- simple and odd python problem HOT 2
- Double-Dueling-DQN: question about the rate to update target network
- Double-Dueling-DQN stops learning
- Can't see the source code. HOT 2
- checkGoal() in gridworld.py
- apply_gradients need a lock?
- A3C-Doom, is threading can make real parallelism?
- Please add more comments..
- Target network updates / Double-Dueling-DQN.ipynb HOT 1
- A3C Doom : function error
- DRQN plays FlappyBird
- what is the mean of multiply (1./(i+1))?
- Reward Smoothing
- A3C Doom: Why there should be no more workers than there are threads on CPU?
- How to do twice training session for the same buffer
- scipy.misc.imresize is deprecated in Scipy 1.14.3 --> modified code HOT 1
- A garbage code in Model-Network.ipynb
- Issue in DRQN
- Crash and burn in TF 2.0 and alter
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 deeprl-agents.