liziniu

ReMax

Code for Paper (ReMax: A Simple, Efficient and Effective Reinforcement Learning Method for Aligning Large Language Models)

policy_optimization

Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)

RL-PPO-Keras

Proximal Policy Optimization(PPO) with Keras Implementation

HyperDQN

Code for ICLR 2022 Paper (HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning)

ISWBC

Code for NeurIPS 2023 Paper (Imitation Learning from Imperfection: Theoretical Justifications and Algorithms)

ILwSD

RLX

RLX is an RL codebase based on TensorFlow. It implements algorithms like SAC, ACER, GAIL and TRPO. It is easy to use.

liziniu.github.io

bib-merge

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

baselines

cgmm

Chinese-LLaMA-Alpaca-2

中文 LLaMA-2 & Alpaca-2 大模型二期项目 + 本地CPU/GPU训练部署 (Chinese LLaMA-2 & Alpaca-2 LLMs)

clash-for-linux

Linux 端使用 Clash 作为代理工具

CVAE

dagger

deep-learning-notes

Experiments with Deep Learning

go-explore

Code for Go-Explore: a New Approach for Hard-Exploration Problems

gym-fetch-stack

gym-minigrid

Minimalistic gridworld package for OpenAI Gym

iclr-blog-track.github.io

Maze

Model-Uncertainty-in-Neural-Networks

TensorFlow implementation of Model-Uncertainty-in-Neural-Networks

random-network-distillation

Code for the paper "Exploration by Random Network Distillation"

rllab-curriculum

sample-efficient-bayesian-rl

Source for the sample efficient tabular RL submission to the 2019 NIPS workshop on Biological and Artificial RL

stable-baselines

SuperMario

webpage-template

Adapted from the widely used project webpage template made by the colorful folks.