Johnny He's repositories
Deep-reinforcement-learning-with-pytorch
PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....
PEER-CVPR23
Authors' implementation of PEER
BEER-ICLR2024
The present anonymous repository serves as a guide for reproducing the results of the "BEER" method proposed in our ICLR submission "Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation".
ERC-ECML-23
Anonymous code for ICML submission 45
ColossalAI
Making large AI models cheaper, faster and more accessible
dalai_llama
The simplest way to run LLaMA on your local machine
deep-successor-features-for-transfer
A reusable framework for successor features for transfer in deep reinforcement learning using keras.
ffn_geyang
Public Repo for the paper "Overcoming The Spectral-Bias of Neural Value Approximation"
learned-fourier-features
Code for the paper "Functional Regularization for Reinforcement Learning via Learned Fourier Features"
LibMTL
A PyTorch Library for Multi-Task Learning
llama
Inference code for LLaMA models
neural-approx-ss-lfi
Codes for ICLR 21 paper: Neural Approximate Sufficient Statistics for Implicit Models
Online-RLHF
A recipe for online RLHF.
RWKV-LM
RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
tqc_pytorch_1epo
Implementation of Truncated Quantile Critics method for continuous reinforcement learning. https://bayesgroup.github.io/tqc/
trl
Train transformer language models with reinforcement learning.
voltron-robotics
Voltron: Language-Driven Representation Learning for Robotics