Zhehui Huang's repositories
torchrl
Pytorch Implementation of Reinforcement Learning Algorithms ( Soft Actor Critic(SAC)/ DDPG / TD3 /DQN / A2C/ PPO / TRPO)
ppo-implementation-details
The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
Explore-RL
Implementing RL algorithms
python-causality-handbook
Causal Inference for the Brave and True. A light-hearted yet rigorous approach to learning about impact estimation and sensitivity analysis.
ml-glossary
Machine learning glossary
cs-video-courses
List of Computer Science courses with video lectures.
envpool
C++-based high-performance parallel environment execution engine for general RL environments.
brax
Massively parallel rigidbody physics simulation on accelerator hardware.
d3rlpy
An offline deep reinforcement learning library
IsaacGymEnvs
Isaac Gym Reinforcement Learning Environments
rsl_rl
Fast and simple implementation of RL algorithms, designed to run fully on GPU.
legged_gym
Isaac Gym Environments for Legged Robots
awesome-isaac-gym
A curated list of awesome NVIDIA Issac Gym frameworks, papers, software, and resources
tacto
Simulator of vision-based tactile sensors.
franka-interface
C++ Library for Interfacing with Libfranka and Frankapy
pytorch_geometric
Graph Neural Network Library for PyTorch
copilot-docs
Documentation for GitHub Copilot
bsuite
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
acme
A library of reinforcement learning components and agents
dm-haiku
JAX-based neural network library
optax
Optax is a gradient processing and optimization library for JAX.
AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
warp-drive
Extremely Fast End-to-End Deep Multi-Agent Reinforcement Learning Framework on a GPU
dm_control
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
mujoco
Multi-Joint dynamics with Contact. A general purpose physics simulator.
sonnet
TensorFlow-based neural network library
pytorch_geometric_temporal
PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
dm_robotics
Libraries, tools and tasks created and used at DeepMind Robotics.
octomap-python
Python binding of the OctoMap library.