gohsyi

PeerLoss

Learning with Noisy Labels by adopting a peer prediction loss function.

cluster_optimization

Course project of SJTU EE357: Computer Network, advised by Prof. Na Ruan. We implemented and improved "A Hierarchical Framework of Cloud Resource Allocation and Power Management using Deep Reinforcement Learning" and achieve a good trade-off between power usage and job latency.

SegNet-ADDA

Course project of SJTU CS386: Digital Image Processing, where I implemented SegNet combined with ADDA, advised by Prof. Bin Sheng

trading_strategy

Course project of SJTU EE359 Data Mining (advised by Prof. Bo Yuan), where we use reinforcement learning to decide trading strategy.

secure_connectivity

Course project of SJTU EE447: Mobile Internet, advised by Prof. Luoyi Fu and Prof. Xinbing Wang. The task is to design a defending strategy to predict and protect the edges that is most likely to be attacked by attackers.

tslda

Replication of paper "Topic Modeling based Sentiment Analysis on Social Media for Stock Market Prediction".

self_alignment

Retrieval-Augmented Self-Alignment (RASA)

alignment-handbook

Robust recipes to align language models with human and AI preferences

alpaca_eval

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

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

cheatsheet

CoPiEr

Co-training for Policy Learning

end-to-end-negotiator

Deal or No Deal? End-to-End Learning for Negotiation Dialogues

exploration-by-disagreement

[ICML 2019] TensorFlow Code for Self-Supervised Exploration via Disagreement

gohsyi.github.io

hyperparallel_machine_learning

course repo for IV-J

L_DMI

Code for NeurIPS 2019 Paper, "L_DMI: An Information-theoretic Noise-robust Loss Function"

LightZero

look_for_words

Looking for words? Try me.

multiagent-particle-envs

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

OvercookedGPT

An OpenAI gym environment to evaluate the ability of LLMs (eg. GPT-4, Claude) in long-horizon reasoning and task planning in dynamic multi-agent settings.

peer_bc_ct

Mirror of Stable-Baselines: a fork of OpenAI Baselines, implementations of reinforcement learning algorithms

RAIN

Official implementation of [RAIN: Your Language Models Can Align Themselves without Finetuning]

rl-baselines-zoo

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

safe-rlhf

Safe-RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

survey

taxi

CUMCM 2019, Problem C

tianshou

An elegant, flexible, and superfast PyTorch deep Reinforcement Learning platform.

torch-ac

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms: A2C and PPO

troubleshooting

All issues I encountered, continuously updating