rssmlite
A lightweight, well-documented, PyTorch-only library for learning RSSM-based (Recurrent State-Space Model) world models — in the DreamerV2/V3 tradition — on Gymnasium environments. Designed to run end-to-end on a free Google Colab T4 GPU with zero external datasets.
Status: early placeholder release (
v0.0.1). This version exists to reserve the package name; it does not yet contain the RSSM implementation. Follow development at github.com/Mattral/rssmlite.
What's coming
RSSM— encoder, GRU-based recurrent state, categorical stochastic latent, decoder, reward head, continue head (swappable GRU/Transformer backbone).RSSMAgent— actor-critic trained entirely on imagined rollouts.ReplayBuffer— sequence storage and fixed-length sampling.- Config-driven support for CartPole, Acrobot, Pendulum, and LunarLander.
- Runnable Colab notebooks with "Open in Colab" badges, zero manual setup.
Install
pip install rssmlite
(v0.0.1 installs only a version marker — the real API arrives in v0.1.0.)
License
MIT — see LICENSE.
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file rssmlite-0.0.1.tar.gz.
File metadata
- Download URL: rssmlite-0.0.1.tar.gz
- Upload date:
- Size: 3.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
cad3c834e316131c9d1d9ab66a0e5c92950059ff839bae8de4a75d9750f00cbd
|
|
| MD5 |
8c5e1f8a4d54852c7c10821f26e6d37d
|
|
| BLAKE2b-256 |
463c39d1a4d0308b617a92b1b736be87709a65802dede0a6489756544ac53fb5
|
File details
Details for the file rssmlite-0.0.1-py3-none-any.whl.
File metadata
- Download URL: rssmlite-0.0.1-py3-none-any.whl
- Upload date:
- Size: 4.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.14.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c256c7745c0ee35aaa52ff6dacaf556938da91bcc4db258eb39b4276d93003c6
|
|
| MD5 |
cdd9be72942f79cb6432a2e565d80ec6
|
|
| BLAKE2b-256 |
eb865c1d8fdb9d20d02be92ea079d097524cd16f676553f610877148b5a5010c
|
