yaqianzhang Goto Github PK

adaptive-quantization-modules

Code for "Online Learned Continual Compression with Adaptive Quantization Modules"

avalanche

Avalanche: an End-to-End Library for Continual Learning based on PyTorch.

aws-ohl-autoaug

An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise Weight Sharing) by Sensetime Research.

backpropthroughthevoidrl

RL Experiments from our paper "Backpropagation Through the Void": https://arxiv.org/abs/1711.00123. Lovingly forked from OpenAI's RL Baseline repo.

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

bdpi

Sample-Efficient Reinforcement Learning with Bootstrapped Dual Policy Iteration

bpg_rllab_plusplus

cil_survey

The code repository for "Deep Class-Incremental Learning: A Survey" in PyTorch.

continual_rl

Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

continualevaluation

[Spotlight ICLR 2023 paper] Continual evaluation for lifelong learning with neural networks, identifying the stability gap.

corrnet

A implementation of the paper "Correlational Neural Networks" (2015)

corrnet-1

Implementation of Correlational Neural Networks using tensorflow

cs231n_computer_vision

Assignment for stanford course CS231n IN 2016

cs294_drl

My solution to CS294-CS294-112: Deep Reinforcement Learning (UC Berkeley; 2017 Fall)

der_library

An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning

dinky

Dinky is a Jekyll theme for GitHub Pages

fast-autoaugment

Official Implementation of 'Fast AutoAugment' in PyTorch.

homework_fall2020

Assignments for Berkeley CS 285: Deep Reinforcement Learning (Fall 2020)

hugo-blog-theme

ict

Code for reproducing ICT ( published in IJCAI 2019)

la-maml

Official Code Repository for La-MAML: Look-Ahead Meta-Learning for Continual Learning"

loss_landscape

Loss landscape analysis for continual learning algorithms

maximally_interfered_retrieval

Codebase for "Online Continual Learning with Maximally Interfered Retrieval"

minimal-mistakes

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

mirage-rl

Code to reproduce the experiments in The Mirage of Action-Dependent Baselines in Reinforcement Learning.

mixmatch

mma

models

Models and examples built with TensorFlow

modify-2048

nonstationarybanditlib