Collection of reinforcement learning algorithms

Implementation of the Large Behavioral Model architecture for dexterous manipulation from Toyota Research Institute

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Robotics research demonstrating reliability and robustness in the real world (continuously updated)

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

🔥Highlighting the top ML papers every week.

Open-source implementation of AlphaEvolve

The official implementation of "Horizon Reduction Makes RL Scalable"

A Python library for dynamic dispatch based on module versions and backends.

Implementation of the world model architecture for self driving out of Wayve

Implementation of Amplify, Actionless Motion Priors for Robot Learning from Videos

Judo: a hackable sampling-based MPC toolbox

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

Continuous Thought Machines, because thought takes time and reasoning is a process.

Fast Discounted Cumulative Sums in PyTorch

The unitree_il_lerobot open-source project is a modification of the LeRobot open-source training framework, enabling the training and testing of data collected using the dual-arm dexterous hands of…

Motion imitation with deep reinforcement learning.

Code for conservative Q-learning

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

Visually explore Python object graphs

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

GSoC report of Chandramouli Rajagopalan under Debian Android Tools

Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

A living collection of deep learning problems