Deepmind Python Packages

pysc2

StarCraft II Learning Environment

nfnets-pytorch

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/

disco-torch

A PyTorch port of DeepMind's Disco103 — the meta-learned reinforcement learning update rule from Discovering State-of-the-art Reinforcement Learning Algorithms (Nature, 2025).

reaver

Reaver: Modular Deep Reinforcement Learning Framework. Focused on StarCraft II. Supports Gym, Atari, and MuJoCo. Matches reference results.

alphagenome-viewer

Web interface for Google DeepMind's AlphaGenome genomic prediction model

turbokv

First open-source implementation of TurboQuant (arXiv 2504.19874) — 4-7x LLM KV cache compression. pip install turbokv

nalu

Basic pytorch implementation of NAC/NALU from Neural Arithmetic Logic Units paper by trask et.al

spriteworld

Spriteworld is a python-based reinforcement learning environment consisting of a 2-dimensional arena with objects that can be freely moved.

turboquant-impl

First open-source implementation of TurboQuant (arXiv 2504.19874) — 4-7x LLM KV cache compression. pip install turbokv