A list of Offline to Online RL papers (continually updated)

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

hand importer and dataset creation tool for poker

The official Python library for the OpenAI API

🦜🔗 The platform for reliable agents.

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

Robust Speech Recognition via Large-Scale Weak Supervision

Example notebooks for Reverse Engineering the Neural Tangent Kernel

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Seminar on Large Language Models (COMP790-101 at UNC Chapel Hill, Fall 2022)

🛠️ Corrected Test Sets for ImageNet, MNIST, CIFAR, Caltech-256, QuickDraw, IMDB, Amazon Reviews, 20News, and AudioSet

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

PyTorch dataset extended with map, cache etc. (tensorflow.data like)

Understanding Deep Networks via Extremal Perturbations and Smooth Masks

CNN for rope state estimation

Fast symbolic computation, code generation, and nonlinear optimization for robotics

Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Rich Image Visualization with Minimum Dependency (no OpenCV, Matplotlib)

Learning to Fill the Seam by Vision: Sub-millimeter Peg-in-hole on Unseen Shapes in Real World

Pre-training Reusable Representations for Robotic Manipulation Using Diverse Human Video Data

Advantage weighted Actor Critic for Offline RL

Tasks to get you started with MineRL

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

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

An offline deep reinforcement learning library

Collection of reinforcement learning algorithms

Massively parallel rigidbody physics simulation on accelerator hardware.

SAPIEN Embodied AI Platform

A PyTorch implementation of Implicit Q-Learning