"모두를 위한 메타러닝" 책에 대한 코드 저장소

《Pytorch模型训练实用教程》中配套代码

该仓库用于记录作者本人参加的各大数据科学竞赛的获奖方案源码以及一些新比赛的原创baseline. 主要涵盖：kaggle, 阿里天池，华为云大赛校园赛，百度aistudio，和鲸社区，datafountain等

文本相似度（匹配）计算，提供Baseline、训练、推理、指标分析...代码包含TensorFlow/Pytorch双版本

[ICML 2021] Official code for SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies

Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information.

DrQ: Data regularized Q

微信大数据2021 1st，qq浏览器2021 3rd，mind新闻推荐2020 1st，NAIC2020 AI+遥感影像 2nd

impact-driven-exploration

Dynamic Bottleneck for Robust Self-Supervised Exploration

DrQ-v2: Improved Data-Augmented Reinforcement Learning

Proximal Policy Optimization (PPO) algorithm for Super Mario Bros

A public repo for ICML 2021 "Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks"

Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

Proto-RL: Reinforcement Learning with Prototypical Representations

A Pytorch-Lightning implementation of self-supervised algorithms

ViZdoomaze includes empty mazes and mazes with obstacles, based on the indoor plans of undecorated departments and build them in ViZDoom, which is a clone of the well-known classic game Doom implem…

applying random convolutions to an image

PyTorch implementation of Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning

Implement many Sparse Reward algorithms in Gym Fetch environment

Master's Thesis Project @ EPFL

Non-official implement of Paper：CBAM: Convolutional Block Attention Module

Maze navigation scenarios for VizDoom