hebowei2000 Goto Github PK

adaptivesystems

RL CIRL Research

ai-chip

A list of ICs and IPs for AI, Machine Learning and Deep Learning.

aichip_paper_list

airsim-neurips2019-drone-racing

Drone Racing @ NeurIPS 2019, built on Microsoft AirSim

albert_zh

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

awesome-cto

A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups

awesome-vision-language-navigation

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

bmagccns

Bioinfomatic motif-matching based Subgraph-level Attentional Convolutional Network for Graph Classifification

bremen

Codebase of Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

c-swm

Contrastive Learning of Structured World Models

clrs

Benchmark for learning 'Algorithm' representation task

cql

Code for conservative Q-learning

cs231n

斯坦福 cs231n 作业代码实践

csapp-labs

Solutions and Notes for Labs of Computer Systems: A Programmer's Perspective 3rd Editon // 《深入理解计算机系统》第三版的实验文件、解答与笔记

cvpr_20200510

cvpr_workshop_extended

d4rl

A benchmark for offline reinforcement learning.

ddpg_slim

ddpg agent using slim!

deep-learning-for-recommendation-systems

This repository contains Deep Learning based articles , paper and repositories for Recommender Systems

deep-reinforcement-learning

worked by bowei he(Buaa) and Alex zhao(Umich)

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

deeprl

Deep Reinforcement Learning Lab, a platform designed to make DRL technology and fun for everyone

dess

Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System

digital_image_process

Completion of basic digital signal process algorithms with c++ and opencv3.4.1

dopamine

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

dreamer

Dream to Control: Learning Behaviors by Latent Imagination

easyocr

Ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai

from-cs-to-agi

A collection of classical computer science books and adavanced materials about deep reinforcement learning ,statistical machine learning and non-convex optimization.