Autoresearch for Go

Flax is a neural network library for JAX that is designed for flexibility.

A minimal implementation of DeepMind's Genie world model

Build 3D Assets with Text Using Gaussian Splatting

Fast and flexible multi-agent gridworld reinforcement learning environments.

RL research on Android devices.

Open AI gym poker environment built using the clubs package

A Real-Time-Strategy game for Deep Learning research

SAC + CPL training humanoids to play piano

From the fundamentals of diffusion to flow matching in pi0

Simulation platform for general-purpose robotics & embodied AI learning.

A deep dive on the history of robotics and the future of humanoids

Hierarchical Reinforcement Learning and Trajectory Optimization on the Unitree Go2

adammaj.com | Built with Next & Chakra

ACT adapted to aloha on bigym tasks with joycon virtual teleop for data collection

Nintendo Switch Teleoperation and ACT autonomy on ALOHA for Bigym benchmark tasks

driver for Joy-Con (Nintendo Switch)

Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

A deep-dive on the entire history of deep-learning

A minimal GPU design in Verilog to learn how GPUs work from the ground up

ALIEN is a CUDA-powered artificial life simulation program.

DDPG, Decision Transformer, I2A with PPO, and SAC self-play on simulated combat humanoids

Novel adaptive random sampling algorithm for kernel density estimation using dimension reduction and shell-spaced kdtree kernel squared evaluation