Costa Huang

cleanrl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

ppo-implementation-details. The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization

portwarden. Create Encrypted Backups of Your Bitwarden Vault with Attachments

lm-human-preference-details. RLHF implementation details of OAI's 2019 codebase

invalid-action-masking. Source Code for A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

summarize_from_feedback_details. Python

cleanba. CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL

PPO-Implementation-Deep-Dive. DEPRECATED - please visit https://github.com/vwxyzjn/ppo-implementation-details

gym-microrts-paper. The source code for the gym-microrts paper.

a2c_is_a_special_case_of_ppo. A2C is a special case of PPO!

jupyter_disqus. Add Disqus to your Jupyter notebook.

SC2AI. Integrated Tensorforce and OpenAI Gym to train SC II game agents.

costa-utils. Python

gym-pysc2. Gym wrapper for pysc2

envpool-cleanrl. Python

free-mujoco-py. MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

LeanRL. LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

ppo-atari-metrics. Python

benchmark-ci. Python

action-guidance. Python

notablog-starter. The official starter project for Notablog.

lm-human-preferences. Code for the paper Fine-Tuning Language Models from Human Preferences

cleangpt. Python

trl. Train transformer language models with reinforcement learning.

minimal-adam-difference. Python

quickchat. Python

microrts. Java

vectorized-value-methods. [WIP] Vectorized architecture for value-based methods such as DQN and DDPG

direct-preference-optimization. Reference implementation for DPO (Direct Preference Optimization)

envpool-xla-cleanrl. Python

entity-ppo-demo. Python

transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

alignment-handbook. Robust recipes for to align language models with human and AI preferences

minimal-uv-deep-ep-gemm-installation. Python

Open-Reasoner-Zero. Official Repo for Open-Reasoner-Zero

optax. Optax is a gradient processing and optimization library for JAX.

hfblog. Public repo for HF blog posts

verl. verl: Volcano Engine Reinforcement Learning for LLMs

cleanba-test. Python

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

zero3_min_repro. Python

envpool_bug. Python

PokemonRedExperiments. Playing Pokemon Red with Reinforcement Learning

Sentiment-Analysis-LSTM. Used neural network to classify movie reviews based on sentiment

embedding_projector. Python

notion-blog. TypeScript

CS583. Python

awesome-vue. A curated list of awesome things related to Vue.js

validate-new-gym-mujoco-envs. Python