Ocarina of Time native on iOS and iPadOS via Ship of Harkinian with Metal rendering, touch controls, controller support, and ROM-free reproducible builds.

A tiny conversational Minionese language model trained from scratch on Apple Silicon

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

A High-Throughput JAX-native Environment for Abstraction and Reasoning Research

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

Pointax: PointMaze Environment for JAX

Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!

RL Environments in JAX 🌍

Partially Observable Benchmarks in JAX

Differentiable Rasteriser implemented in JAX. Reference: https://github.com/erwincoumans/tinyrenderer, https://github.com/ssloy/tinyrenderer/wiki; PR: https://github.com/google/brax/pull/367

Massively parallel rigidbody physics simulation on accelerator hardware.

Jax/Flax Implementation of TD-MPC2

Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy

⚡ Flashbax: Accelerated Replay Buffers in JAX

A compositional diagramming and animation library as an eDSL in Python

Monte Carlo tree search in JAX

Official reinforcement learning environment for demand response and load shaping

Accelerated minigrid environments with JAX

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

RL Environments in JAX 🌍

A collection of postmortems. Sorry for the delay in merging PRs!

An elegant PyTorch deep reinforcement learning library.

A collection of reference environments for offline reinforcement learning

Partially Observable Process Gym

Lightweight python library for launching experiments and tuning hyperparameters, either locally or on a cluster

From search engines, to science, to robotics, this reposity is meant to showcase the use of reinforcement learning in the world..