Rui

Sparse-Reward-Algorithms. Implement many Sparse Reward algorithms in Gym Fetch environment

RiC. Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"

Generalizable-Reward-Model. Code for NeurIPS 2024 paper "Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs"

2048_env. 2048 environment for Reinforcement Learning and DQN algorithm

AWGCSL. Code for ICLR 2022 paper Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL.

RORL. Code for NeurIPS 2022 paper "Robust offline Reinforcement Learning via Conservative Smoothing"

RIQL. [ICLR 2024 Spotlight] Code for ICLR 2024 paper "Towards Robust Offline Reinforcement Learning under Diverse Data Corruption"

Modular_HER. Modular-HER is revised from OpenAI baselines and supports many improvements for Hindsight Experience Replay as modules.

Model-basedHER. Model-based Hindsight Experience Replay

GOAT. Code for the ICML 2023 paper "What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?".

Txt_to_timeline. A python tool to make a beautiful timeline by writing a txt file like diary.

Random-network-distillation_complete. add test function and my trained models to the original codes of random-network-distillation of openai

Ivision_Server. 兴趣团队微信小程序后端，用于后来者参考和改进

HERO. code for Combining Hindsight and Imagination in Multi-goal ReinforcementLearning

UWMSG. Python

Ivision_Weichat_Applet. 兴趣团队微信小程序前端，可供后来者参考和改进

Picture-Cloud-Factory-master. A WeChat applet using image process tech and AI method.

yangrui2015.github.io. JavaScript

COMP4901Y_Course_HKUST. Course Material for the UG Course COMP4901Y

reward-bench. RewardBench: the first evaluation tool for reward models.

vpn. 快速搭建一个自己的VPN科学上网,搭建ss并开启bbr快速上网

rlkit_pro. Improving original rlkit forked from https://github.com/vitchyr/rlkit

starter-academic. Jupyter Notebook

Some-Pattern-Recognition-Methods-Implementation. I think our Pattern Recognition Class's homework is quite interesting, so I place my code here for sharing, please check.

d3rlpy. An offline deep reinforcement learning library

Deep-reinforcement-learning-with-pytorch. PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....