Code for Deep RL from Human Preferences [Christiano et al]. Plus a webapp for collecting human feedback

Code for the paper Fine-Tuning Language Models from Human Preferences

LightSim2grid implements a c++ backend targeting the Grid2Op (https://github.com/rte-rance/grid2op) platform.

L2RPN Baselines a repository to host baselines for l2rpn competitions.

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning

Implementations of DQN, DQN with PER, DDQN with PER, and DDDQN with PER agents to maximise reward in a 14 node power grid station

An open-source PyTorch code for crowd counting

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

Multi-Person Pose Estimation System

Feature Pyramid Networks for Object Detection

Models and examples built with TensorFlow

home page

demo code of my blog

一键人脸归一化处理工具，包括人脸检测，人脸关键点检测，基于关键点的人脸对齐