Scalable neural net training via automatic normalization in the modular norm.

PyTorch Package For Quasimetric Learning

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

PyTorch extensions for high performance and large scale training.

Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"

Code for "Temporal Difference Learning for Model Predictive Control"

A 2D physics engine for simulating dynamical billiards.

HIQL: Offline Goal-Conditioned RL with Latent States as Actions (NeurIPS 2023)

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

Collections of CS PhD Application Fee Waivers of schools in North America

ASGI specification and utilities

Official implementation of FIND (NeurIPS '23) Function Interpretation Benchmark and Automated Interpretability Agents

The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning or fine-tuning. Training is reward-free and based on the Fo…

Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023

Computational framework for reinforcement learning in traffic control

MTM Masked Trajectory Models for Prediction, Representation, and Control.

A minimal and stable PPO.

Lightweight, useful implementation of conformal prediction on real data.

Folklore facts on probability distribution learning, testing, and whatever-ing

Reparameterize your PyTorch modules

Code for Debiasing Vision-Language Models via Biased Prompts

Demystify RAM Usage in Multi-Process Data Loaders

MoCo with Alignment and Uniformity Loss.

RoboDesk with A Diverse Set of Distractors