adversarial-finetuning

alignmentstudy

variants of Inverse Reinforcement Learning

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

causal-text-embeddings-tf2

Tensorflow 2 implementation of Causal-BERT

cifar-vgg

VGG16 models for CIFAR-10 and CIFAR-100 using Keras

count_pile_name_freq

crazyflie_human

ROS wrapper for pedestrian prediction.

crossattentioncontrol

Unofficial implementation of "Prompt-to-Prompt Image Editing with Cross Attention Control" with Stable Diffusion

cuad

CUAD (NeurIPS 2021)

fastertransformer

Transformer related optimization, including BERT, GPT

github-actions-for-packages

goalstructure

imitation-extern

CHAI's imitation repo + benchmarking against SB GAIL

inverse_rl

kfac

An implementation of KFAC for TensorFlow

langchain

⚡ Building applications with LLMs through composability ⚡

mc_scripts

Tooling

minerl

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

motd-swapper

mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

neural-mmo

Neural MMO - A Massively Multiagent Game Environment

nng

building off of pomonam/NoisyNaturalGradient.

noisynaturalgradient

Pytorch Implementation of paper "Noisy Natural Gradient as Variational Inference"

noisynaturalgradient-1

TensorFlow implementation of "noisy K-FAC" and "noisy EK-FAC"

packet-tools

pedestrian_prediction

realtime, confidence-varying trajectory prediction for "Probabilistically Safe Robot Planning with Confidence-Based Human Predictions". RSS '18

polyjuice

qmsum

Dataset for NAACL 2021 paper: "QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization"

restic-systemd-automatic-backup

My restic backup solution using Backblaze B2 storage, systemd timers (or cron) and email notifications on failure.

rllab

rllab is a framework for developing and evaluating reinforcement learning algorithms, fully compatible with OpenAI Gym.