hejia-zhang
PhD in CS (Robotics & AI) from USC; Robot Learning for Manipulation; Embodiment Foundation Models; Task-and-Motion Planning
@icaros-uscLos Angeles, USA
Pinned Repositories
Auto-Conditioned-LSTM
Implementation of Auto-Conditioned LSTM using TensorFlow
awesome-model-based-reinforcement-learning
A curated list of awesome Model-based reinforcement learning resources
BenchTAMP
hjzh4.github.io_old
My personal website and my blog. Please fire an issue if you have any question about my blogs.
libwave
C++ library for hardware-accelerated video stream decoding
MiniRLILLib
Nao-bindings
Use this to run your algorithms on Nao robot.
milp_constrained_gan
Using MILP to encode constraints of generated game levels.
aikido
Artificial Intelligence for Kinematics, Dynamics, and Optimization
garage
A toolkit for reproducible reinforcement learning research.
hejia-zhang's Repositories
hejia-zhang/BenchTAMP
hejia-zhang/MiniRLILLib
hejia-zhang/3D-VLA
[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model
hejia-zhang/ai-deadlines
:alarm_clock: AI conference deadline countdowns
hejia-zhang/AI-lectures
Lecture slides and scripts (LaTeX sources) in AI, Robotics, Machine Learning, Maths, Optimization
hejia-zhang/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.
hejia-zhang/downward
hejia-zhang/fairo
A modular embodied agent architecture and platform for building embodied agents
hejia-zhang/gpt4-image-api
Small tool using selenium to get a temporary API endpoint for the ChatGPT Image Input / image recognition feature. Very quickly made, you should not rely on this on prod.
hejia-zhang/HTN-Translation
Translating HTN planning problems to PDDL
hejia-zhang/installation-guides
Centralized administration of dependency installation guides.
hejia-zhang/jaco_description
hejia-zhang/manicast
hejia-zhang/motion-planners
Python implementations of several robotic motion planners
hejia-zhang/OMTPlan
A python framework for Optimal Planning Modulo Theories
hejia-zhang/openvpn-setup
hejia-zhang/PantheonRL
PantheonRL is a package for training and testing multi-agent reinforcement learning environments. PantheonRL supports cross-play, fine-tuning, ad-hoc coordination, and more.
hejia-zhang/pddlstream
PDDLStream: Integrating Symbolic Planners and Blackbox Samplers
hejia-zhang/peract_docker
hejia-zhang/PPO-PyTorch
Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
hejia-zhang/rewd_controllers
master
hejia-zhang/ros2-humble-docker-dev
hejia-zhang/softgym
SoftGym is a set of benchmark environments for deformable object manipulation.
hejia-zhang/stock-rnn
Predict stock market prices using RNN model with multilayer LSTM cells + optional multi-stock embeddings.
hejia-zhang/symk
Sym-k is a state-of-the-art top-k planner.
hejia-zhang/URDF2MJCF
hejia-zhang/UVD
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
hejia-zhang/VAE-CVAE-MNIST
Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch
hejia-zhang/welcome_assignments_sols
hejia-zhang/YARR
Yet Another Robotics and Reinforcement (YARR) learning framework for PyTorch.