ruoyuGao

awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

DI-engine

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

AIRL

my implementation with adversarial inverse reinforcement learning on gym(breakout)

anonymize-slide

Delete the label from a whole-slide image

awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

CloudComputing

some useful skills for azure, aws and gcp

Dynamo

simplified Dynamo with hash consistent, anti-entropy and gossp protocol

Genshin_auto_harvesting

genshin automatic harvesting AI is composed of [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX), DQN two-part model. Use transfer learning for training.We use yolox to detect the pixel coordinates of characters and items in the picture, and convert this information into our custom state information, and use DQN to make decisions.

mnist_app_android

a app for you to transfer tf model to android.you can wirte a number by your hand and predict it by app

scikit-opt-gpu

We implemented our own sequential version of GA, PSO, SA and ACA using C++ (some using Eigen3 as matrix operation backend) and the parallelized version with CUDA support. All of them are much faster than the popular lib scikit-opt.

ruoyuGao/scikit-opt-gpu

We implemented our own sequential version of GA, PSO, SA and ACA using C++ (some using Eigen3 as matrix operation backend) and the parallelized version with CUDA support. All of them are much faster than the popular lib scikit-opt.

ruoyuGao/AIRL

my implementation with adversarial inverse reinforcement learning on gym(breakout)

ruoyuGao/Dynamo

simplified Dynamo with hash consistent, anti-entropy and gossp protocol

ruoyuGao/Genshin_auto_harvesting

genshin automatic harvesting AI is composed of [YOLOX](https://github.com/Megvii-BaseDetection/YOLOX), DQN two-part model. Use transfer learning for training.We use yolox to detect the pixel coordinates of characters and items in the picture, and convert this information into our custom state information, and use DQN to make decisions.

ruoyuGao/CloudComputing

some useful skills for azure, aws and gcp

ruoyuGao/anonymize-slide

Delete the label from a whole-slide image

ruoyuGao/awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

ruoyuGao/DI-engine

OpenDILab Decision AI Engine

ruoyuGao/mnist_app_android

a app for you to transfer tf model to android.you can wirte a number by your hand and predict it by app

ruoyuGao/DI-engine-docs

DI-engine docs (Chinese and English)

ruoyuGao/gym

local gym contain boxworld

ruoyuGao/Judd-Ofelt

ruoyuGao/leetcode_practice

ruoyuGao/personal_slurm_script

ruoyuGao/products

NYU DevOps Products Service Spring 2023

ruoyuGao/ruoyuGao

ruoyuGao/ruoyuGao.github.io