A minimal Decision Transformer implementation for Minari datasets.
Project description
nanoDT
The simplest, fastest repository for training/finetuning medium-sized DTs.
This repository is based on nanoGPT and provides a lightweight implementation of Decision Transformers.
Features
- Lightweight and Simple: Minimal dependencies and easy-to-understand codebase.
- Continuous and Discrete Action Spaces: Works seamlessly with both types of environments.
- Customizable Models: Easily configure model architecture and training parameters.
- Dataset Integration: Supports Minari datasets for training.
- Scalable Training: Optimized for fast training on GPUs.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nanodt-0.1.0.tar.gz
(35.5 kB
view details)
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
nanodt-0.1.0-py3-none-any.whl
(15.4 kB
view details)
File details
Details for the file nanodt-0.1.0.tar.gz.
File metadata
- Download URL: nanodt-0.1.0.tar.gz
- Upload date:
- Size: 35.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.7.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3b880c24f9c076d7d43976719880e59e01db10d189cf563fbe78174f11dd6477
|
|
| MD5 |
4dd21da1de8101a97297263d79be83a8
|
|
| BLAKE2b-256 |
5ee1daaf8c27055907ba1a8e53d909eda3b36682e3e1c51e5bb75bb1d83cfe66
|
File details
Details for the file nanodt-0.1.0-py3-none-any.whl.
File metadata
- Download URL: nanodt-0.1.0-py3-none-any.whl
- Upload date:
- Size: 15.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.7.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1ab58781aec26afa4969038b2c25ff7063a9ce83b74c75972886a8e1c87bb6b8
|
|
| MD5 |
fdea93198ac1b87401948348c77f9d03
|
|
| BLAKE2b-256 |
bf20193c5b96ec5a8276bbf75df25031adabdeea68d33cf51b62e757bd21cd2b
|
