Comments (8)
Hi @joaogui1! It would be great to see a DQN example, and perhaps it's even a good idea to use RLAX (if RLAX is general purpose enough to work with any JAX codebase)
But I'm not sure we'll be taking this into flax/examples/. We want to encourage the flourishing of an ecosystem of examples, and not all of them can or should be held to the very high maintenance expectations of flax/examples.
We'll start linking to many GitHub repositories of Flax projects from our README, so my suggestion is to go ahead and build your DQN repo and we'll link to it. Then we could potentially consider bringing that into flax/examples but we'd need one of the Flax OWNERS to take responsibility for it, which involves performance monitoring, commitment to modifications with future API changes, and more.
from flax.
Actually, in particular I would be interested to see what a DQN example with or without RLAX looks like, is that something that would be pretty straightforward to try out?
from flax.
So @avital , I already have the version without rlax (the "tense" version if you will): colab
Though I need some help making it prettier/more idiomatic, specially with the act part which I ended up commenting
I will code a version with rlax and try to put here before the weekend
from flax.
Here's the rlax version @avital
from flax.
Awesome @joaogui1 ! Your examples looks very cool and it would be great if we could link to this from our examples page. Would you be willing to put your example in a separate Github repository, with some instructions on what it is and how to run it? Then we will add a link to it from our example page.
from flax.
Like this @marcvanzee ?
from flax.
Just pinging @marcvanzee
from flax.
@marcvanzee -- can you add this to the table in examples/README.md
? https://github.com/joaogui1/RL-JAX/tree/master/DQN
from flax.
Related Issues (20)
- Feature request: Add ConvGRUCell
- The Error in FLOP Computation of Model Tabulate Function HOT 1
- Make redundant `features` argument optional for recurrent cells HOT 2
- Add `reset_gate` flag to `MGUCell` HOT 4
- Unify behavior of strides arg of Conv and ConvTranspose HOT 1
- modifying params of flax.linen. Module model HOT 1
- Error when calling module tabulate involving WeightNorm HOT 5
- Compatibility with Torch LSTM HOT 2
- Wrong parameter names when nesting Modules within flax transformations HOT 3
- Neural Net Training is bottlenecked by maxed out CPU
- Error occurs in `nn.vmap` while `variable_axes` is a nested dict HOT 1
- flax.linen.module.init still fails under dynamic type checking for nested modules
- *Module Parameters* section of docs is outdated. HOT 4
- More memory consume compared with Pytorch HOT 1
- Difference in output between jitted and non-jitted call
- Error when calling `Module.tabulate` on normalization wrappers like `WeightNorm` and `SpectralNorm`
- Orbax checkpoint for LogicallyPartitioned params HOT 2
- For some reason these imports are elided on read the docs
- Using variable declared at a broader scope in a function is bad form HOT 1
- Add `BatchRenorm` layer to `linen.normalization`
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 flax.